Neutrinos From Deep Inside Earth Provide a New Picture of the Mantle
A global constellation of neutrino detectors is creating a never-before-seen view of the radioactive elements that power Earth’s tectonic heat engine.
How Does Touch Lead To Pain Or Pleasure?
Neuroscientist Ishmail Abdus-Saboor discusses efforts to understand how skin contact can be painful or pleasurable, and what touch-obsessed naked mole rats might teach us about human social behavior.
Corals Spin Tiny Vortices to Get Oxygen, but Not if It’s Too Hot
New research is helping biologists understand how an overlooked aspect of coral physiology may affect their fate under climate change.
Why the Legendary Erdős Problems Are Falling to AI
AI’s greatest mathematical successes have come from answers to problems posed by a mid-20th century iconoclast. By examining what makes the Erdős problems unique, mathematicians are trying to understand how AI might change the rest of math.
Is AI Reasoning Right for the Wrong Reasons?
The idea that artificial intelligence can “reason” is more intuitive than ever. But intuitions can be wrong, and the science is far from settled.
What's New
Top 5 Across All Sources-
Neutrinos From Deep Inside Earth Provide a New Picture of the Mantle
Quanta Magazine · 22h ago -
TutorMoments: Do AI tutors know when to help and when to hold back?
Ai2 Blog · 1d ago -
MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification
cs.LG updates on arXiv.org · 1d ago -
When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters
cs.LG updates on arXiv.org · 1d ago -
PPDL: LLM-Based Flows as Probabilistic Programs
cs.LG updates on arXiv.org · 1d ago
Gigafeed (2925 entries)
Neutrinos From Deep Inside Earth Provide a New Picture of the Mantle Quanta Magazine · 22h ago TutorMoments: Do AI tutors know when to help and when to hold back? Ai2 Blog · 1d ago MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification cs.LG updates on arXiv.org · 1d ago When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters cs.LG updates on arXiv.org · 1d ago PPDL: LLM-Based Flows as Probabilistic Programs cs.LG updates on arXiv.org · 1d ago Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language cs.LG updates on arXiv.org · 1d ago Disentangling 3D Modeling from Spatial Reasoning cs.LG updates on arXiv.org · 1d ago Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models cs.LG updates on arXiv.org · 1d ago PRISM: Priority-aware Rubric Internalization via Structured Multimodal Data Synthesis cs.LG updates on arXiv.org · 1d ago Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning cs.LG updates on arXiv.org · 1d ago Beyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuning cs.LG updates on arXiv.org · 1d ago An Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language Goals cs.LG updates on arXiv.org · 1d ago Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction cs.LG updates on arXiv.org · 1d ago Rectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEG cs.LG updates on arXiv.org · 1d ago QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding cs.LG updates on arXiv.org · 1d ago DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting cs.LG updates on arXiv.org · 1d ago Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics cs.LG updates on arXiv.org · 1d ago Spectral Distillation: From Nonlinear Dynamics to Linear State-Space Models cs.LG updates on arXiv.org · 1d ago Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples cs.LG updates on arXiv.org · 1d ago IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games cs.LG updates on arXiv.org · 1d ago Why the Third Axis Is Freedom cs.LG updates on arXiv.org · 1d ago EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents cs.LG updates on arXiv.org · 1d ago Quality Diversity for Reliable Data Driven Time-Use Optimization stat.ML updates on arXiv.org · 1d ago A Unified Causal Inference Framework for the Desirability of Outcome Ranking Paradigm in Benefit-Risk Evaluation stat.ML updates on arXiv.org · 1d ago Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data stat.ML updates on arXiv.org · 1d ago Handling Missing Data in Probabilistic Regression Trees stat.ML updates on arXiv.org · 1d ago Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction stat.ML updates on arXiv.org · 1d ago Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification stat.ML updates on arXiv.org · 1d ago Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning stat.ML updates on arXiv.org · 1d ago Optimal Rates for Learning with Monotone Adversaries stat.ML updates on arXiv.org · 1d ago Scalable estimation of VARMA models stat.ML updates on arXiv.org · 1d ago FlowAdam: Implicit Regularization via Geometry-Aware Soft Momentum Injection stat.ML updates on arXiv.org · 1d ago The Loss Does Not See the Basis, but Adam Does stat.ML updates on arXiv.org · 1d ago Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models stat.ML updates on arXiv.org · 1d ago Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes stat.ML updates on arXiv.org · 1d ago Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty stat.ML updates on arXiv.org · 1d ago Innovation-Residual Auditing of Autonomous Analysis Agents: Localization, Detection Limits, Error Control, and Identifiability stat.ML updates on arXiv.org · 1d ago Structured Dimension-Matched Joint Variational Transdimensional Inference stat.ML updates on arXiv.org · 1d ago Fuzzy network jump models for soft dynamic clustering of graph-structured data stat.ML updates on arXiv.org · 1d ago Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators stat.ML updates on arXiv.org · 1d ago The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity stat.ML updates on arXiv.org · 1d ago Surv-IPTB: An Attention-Based Model for Estimating Individual Probability of Treatment Benefit with Survival Data stat.ML updates on arXiv.org · 1d ago AI-based augmentation of oncology clinical trials Machine learning : nature.com subject feeds · 1d ago Scaling Categorical Flow Maps Apple Machine Learning Research · 1d ago Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models Apple Machine Learning Research · 1d ago Arbitrage: Efficient Reasoning via Advantage-Aware Speculation Apple Machine Learning Research · 1d ago WeatherNext: AI model achieves breakthrough in forecasting cyclones Google DeepMind News · 1d ago How Does Touch Lead To Pain Or Pleasure? Quanta Magazine · 1d ago Ai2 expands collaboration with Hugging Face to accelerate open science Ai2 Blog · 2d ago C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning cs.LG updates on arXiv.org · 2d ago On Hamming-Lipschitz Type Stability of the Subdominant (Minmax) Ultrametric: Theory and Simple Proofs cs.LG updates on arXiv.org · 2d ago A Trust-region Framework for Moment Estimation cs.LG updates on arXiv.org · 2d ago Learning to Resolve Neutron Resonances with Fully Convolutional Neural Networks cs.LG updates on arXiv.org · 2d ago Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation cs.LG updates on arXiv.org · 2d ago An Explainable LLM Agent Layer for Open-World Anomaly Detection in Oil Wells cs.LG updates on arXiv.org · 2d ago Tactus: Open-Vocabulary Object Recognition from Low-Cost Pressure Arrays cs.LG updates on arXiv.org · 2d ago Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity cs.LG updates on arXiv.org · 2d ago Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs cs.LG updates on arXiv.org · 2d ago CAMP: A Cycle-Aware Multi-Scale Patch Mixer for Time Series Forecasting cs.LG updates on arXiv.org · 2d ago LaPrune: Controllable Differentiable Sparsity at Million Scale cs.LG updates on arXiv.org · 2d ago SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors cs.LG updates on arXiv.org · 2d ago Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms cs.LG updates on arXiv.org · 2d ago Spatiotemporal Graph Transformer for Traffic Intelligence in Edge Computing cs.LG updates on arXiv.org · 2d ago SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization cs.LG updates on arXiv.org · 2d ago Out-Of-The-Loop Multi-Fidelity Bayesian Optimization cs.LG updates on arXiv.org · 2d ago LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling cs.LG updates on arXiv.org · 2d ago MINT: Tensor Decomposition on Stacked Recurrence Matrices for Time Series Data Mining cs.LG updates on arXiv.org · 2d ago Understanding Fault Tolerance of Adversarially Robust Pruned Models cs.LG updates on arXiv.org · 2d ago TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction and a Tabular Foundation Model cs.LG updates on arXiv.org · 2d ago Statistical learning theory and Occam's razor: Regularization stat.ML updates on arXiv.org · 2d ago Automatic Statistical Test for Rationally Expressible Algorithms by Selective Inference, with Applications to Feature Selection stat.ML updates on arXiv.org · 2d ago Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds stat.ML updates on arXiv.org · 2d ago Stable Density Ridges: Consistency and Convergence of Subspace Constrained Mean Shift stat.ML updates on arXiv.org · 2d ago Informational Frustration in Neural Manifolds: Shannon Bottlenecks and the Limits of Learnability stat.ML updates on arXiv.org · 2d ago Statistical Mechanics of Learning on Product Wasserstein Manifolds stat.ML updates on arXiv.org · 2d ago Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport stat.ML updates on arXiv.org · 2d ago When Is a Conformal Guarantee Fair? Auditing Silent Subgroup Under-Coverage in Alzheimer's Disease Longitudinal Prediction stat.ML updates on arXiv.org · 2d ago Sample Complexity of Multicalibration for Multilevel Properties stat.ML updates on arXiv.org · 2d ago ArborEnum: Decision Tree Rashomon Sets over Continuous Features stat.ML updates on arXiv.org · 2d ago Achieving First-Order Statistical Improvements in Data-Driven Optimization: From No-Free-Lunch to Amplified Decision Perturbation stat.ML updates on arXiv.org · 2d ago Equitable System-Prompt Selection via Constrained Mixed-Strategy GroupDRO stat.ML updates on arXiv.org · 2d ago iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data stat.ML updates on arXiv.org · 2d ago Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics stat.ML updates on arXiv.org · 2d ago Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation stat.ML updates on arXiv.org · 2d ago An adaptive split-combine Gaussian mixture filter for nonlinear and multimodal state estimation stat.ML updates on arXiv.org · 2d ago Discretization and Statistical Consistency of Functional Flow Matching stat.ML updates on arXiv.org · 2d ago An entropic explanation of insistence on sameness in autism stat.ML updates on arXiv.org · 2d ago Personalized Federated Sparse Adaptation of Time-Series Foundation Models stat.ML updates on arXiv.org · 2d ago Nonparametric Goodness-of-fit Testing under Covariate Shift stat.ML updates on arXiv.org · 2d ago Inference of tumor spatial habitats Machine learning : nature.com subject feeds · 2d ago AI agents are checking the scientific literature — and spotting decades-old errors Machine learning : nature.com subject feeds · 2d ago Locking Pretrained Weights via Deep Low-Rank Residual Distillation Apple Machine Learning Research · 2d ago DeepAmbigQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness Apple Machine Learning Research · 2d ago Corals Spin Tiny Vortices to Get Oxygen, but Not if It’s Too Hot Quanta Magazine · 2d ago 34 Amazon Research Awards Build on Trainium recipients announced Amazon Science homepage · 2d ago Deep Divide-and-Reduce in Symbolic Regression cs.LG updates on arXiv.org · 3d ago Multimodal Auto-regressive Transformer Surrogate for Modeling Variable Operations and Quantifying Uncertainty in Geological Carbon Storage cs.LG updates on arXiv.org · 3d ago LLMs Can Annotate Attribution Graphs cs.LG updates on arXiv.org · 3d ago GeoID-PINN: Identifiability-Aware Regional Epidemic Inference with Geographic Coupling cs.LG updates on arXiv.org · 3d ago Verifier-Guided Model Discovery for Physical Dynamical Systems with Pretrained Symbolic Transformers cs.LG updates on arXiv.org · 3d ago CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study cs.LG updates on arXiv.org · 3d ago Sphere Retraction Normalizations cs.LG updates on arXiv.org · 3d ago Learning Molecular Representations from Cellular Phenotypes with Structure Preservation cs.LG updates on arXiv.org · 3d ago GLOBE: Trajectory-Aligned Gradient Matching with Structured SparseOptimization for Coreset Selection cs.LG updates on arXiv.org · 3d ago Output-Aware Rotation for INT2 KV-Cache Quantization cs.LG updates on arXiv.org · 3d ago PatTree: a novel approach for automated creation of multimodal, graph-based patient representations for medical classification tasks cs.LG updates on arXiv.org · 3d ago Measuring Explainer Stability via Attribution Separability cs.LG updates on arXiv.org · 3d ago NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory cs.LG updates on arXiv.org · 3d ago Can Training Logs Make Model Comparisons More Precise? cs.LG updates on arXiv.org · 3d ago Designing a Good Virtual Node: Addressable and Cardinality-Preserving Global Memory for Message Passing Architectures cs.LG updates on arXiv.org · 3d ago Neural Networks with Local Converging Inputs for Efficient Options Pricing Models cs.LG updates on arXiv.org · 3d ago Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment cs.LG updates on arXiv.org · 3d ago Topological Simplification in Predictive Coding Networks cs.LG updates on arXiv.org · 3d ago Wiring Beats Blending: What Transfers Between Transformer Sizes -- and What Doesn't cs.LG updates on arXiv.org · 3d ago NOMADD: Numerical Optimization of Models Adapting to Data Drift cs.LG updates on arXiv.org · 3d ago A Hyperfinite Framework for Score-Based Generative Modeling stat.ML updates on arXiv.org · 3d ago Particle-based Generalised Stochastic Optimisation stat.ML updates on arXiv.org · 3d ago Causal Inference with Unstructured Outcomes stat.ML updates on arXiv.org · 3d ago Minimax-Optimal Semiparametric Contextual Dynamic Pricing with Multimodal Revenue stat.ML updates on arXiv.org · 3d ago Conformal risk control for model-form uncertainty in parametric non-intrusive reduced-order models stat.ML updates on arXiv.org · 3d ago Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking stat.ML updates on arXiv.org · 3d ago Divide-and-Conquer: Towards Generalizable Amortized Bayesian Inference for the Drift Diffusion Model stat.ML updates on arXiv.org · 3d ago Robust Low-Tubal-Rank Tensor Completion under Cross-Concentrated Sampling stat.ML updates on arXiv.org · 3d ago Information-Geometric Forward Policy Training in GFlowNets stat.ML updates on arXiv.org · 3d ago Neural network realization of binary refinement iterates via a two-chart atlas selector stat.ML updates on arXiv.org · 3d ago GeoID-PINN: Identifiability-Aware Regional Epidemic Inference with Geographic Coupling stat.ML updates on arXiv.org · 3d ago Can Training Logs Make Model Comparisons More Precise? stat.ML updates on arXiv.org · 3d ago DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing stat.ML updates on arXiv.org · 3d ago Tight Information Complexity of the Coin Problem in the Broadcast Model stat.ML updates on arXiv.org · 3d ago Improved Quantum Algorithms for Reinforcement Learning Under a Generative Model stat.ML updates on arXiv.org · 3d ago When Predictions Become Regressors: A Split-Sample Correction for Biases in Downstream Inference stat.ML updates on arXiv.org · 3d ago Calibrated Bayesian Inference for Stochastic Intervention Effects stat.ML updates on arXiv.org · 3d ago Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores stat.ML updates on arXiv.org · 3d ago Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework stat.ML updates on arXiv.org · 3d ago A Direct Route to Markov Chain Convergence via Asymptotic Equivalence with the Target stat.ML updates on arXiv.org · 3d ago The Virtual Tissues foundation model resolves spatial proteomics across scales Machine learning : nature.com subject feeds · 3d ago Taming Outlier Tokens in Diffusion Transformers Apple Machine Learning Research · 3d ago Solving the solvent problem MIT News - Artificial intelligence · 3d ago The benefits of medical AI assistance vary based on user expertise MIT News - Artificial intelligence · 4d ago The benefits of medical AI assistance vary based on user expertise MIT News - Machine learning · 4d ago Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language Models cs.LG updates on arXiv.org · 4d ago Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark cs.LG updates on arXiv.org · 4d ago MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing cs.LG updates on arXiv.org · 4d ago Progressive$^2$: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression cs.LG updates on arXiv.org · 4d ago Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset cs.LG updates on arXiv.org · 4d ago Leak It: A Probabilistic Approach to Training-Data Extraction from Black-Box Language Models cs.LG updates on arXiv.org · 4d ago Response Magnitude as a Dominant Signal for Held-Out CRISPRi Perturbation Effect Prediction cs.LG updates on arXiv.org · 4d ago Inference-Time Policy Alignment for Fair Reinforcement Learning cs.LG updates on arXiv.org · 4d ago AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery cs.LG updates on arXiv.org · 4d ago A Physics-Chemistry-Informed Neural Network (PCINN) for Real-Time Spatial-ALD Coverage Prediction and Reliable Kinetics Inversion cs.LG updates on arXiv.org · 4d ago Verifier-Induced Support Reshaping in On-Policy Optimization cs.LG updates on arXiv.org · 4d ago Similarity-Aware Machine Unlearning cs.LG updates on arXiv.org · 4d ago Stabilized Best-of-$K$ Training for Neural Combinatorial Optimization cs.LG updates on arXiv.org · 4d ago Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning cs.LG updates on arXiv.org · 4d ago Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch cs.LG updates on arXiv.org · 4d ago Neural operator learning for collision-aware trajectory planning of spacecraft swarms cs.LG updates on arXiv.org · 4d ago Ensemble of Unsupervised Deep Learning for Clustering Imbalanced Tabular Data cs.LG updates on arXiv.org · 4d ago Modeling Unknown Nonlocal PDE Systems via Flow Map Learning cs.LG updates on arXiv.org · 4d ago DSETA: A Dual-Stage Continual Learning Framework for Travel Time Prediction in Dynamic Traffic Environments cs.LG updates on arXiv.org · 4d ago Unleashing the Potential of Large Language Models: A Blueprint for Real-Time, Enterprise-Ready Deployments cs.LG updates on arXiv.org · 4d ago A reproducible and extensible framework for benchmarking competing risks survival models stat.ML updates on arXiv.org · 4d ago Causal Inference with Unstructured Treatments stat.ML updates on arXiv.org · 4d ago Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors stat.ML updates on arXiv.org · 4d ago Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP stat.ML updates on arXiv.org · 4d ago How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule stat.ML updates on arXiv.org · 4d ago Dominant Arm Identification with Mixing and Recycling Observed Samples stat.ML updates on arXiv.org · 4d ago Finite-Probe Total-Variation Certificates for Finite-Basis Drifting Models stat.ML updates on arXiv.org · 4d ago The Label Defines the Timescale: Trait-State Limits of Temporal-Aggregate Learning stat.ML updates on arXiv.org · 4d ago Detecting Nonproperness of Likelihood Equations stat.ML updates on arXiv.org · 4d ago Private Generative Bootstrap via Blocking stat.ML updates on arXiv.org · 4d ago Computational and Statistical Guarantees of the \textit{c}-Rectified flow stat.ML updates on arXiv.org · 4d ago Interaction Is Not Necessary for Order-Optimal 1-Bit Mean Estimation stat.ML updates on arXiv.org · 4d ago Fast-Mixing Markov Chains without Gradients stat.ML updates on arXiv.org · 4d ago Bridging extrinsic and intrinsic variable importance stat.ML updates on arXiv.org · 4d ago Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch stat.ML updates on arXiv.org · 4d ago Backward Bayesian Outcome Weighted Learning stat.ML updates on arXiv.org · 4d ago Recursive Gaussian Processes and the Bayesian Brain stat.ML updates on arXiv.org · 4d ago Learning the Pareto Frontier of Predictive Models under Distribution Shift stat.ML updates on arXiv.org · 4d ago Evolutionary Curriculum Learning Improves Biological Sequence Modeling stat.ML updates on arXiv.org · 4d ago Physics-informed neural networks for two-dimensional wall-reactive solute dispersion in canonical shear flows stat.ML updates on arXiv.org · 4d ago Privacy risks from medical AI tools are not shared equally Machine learning : nature.com subject feeds · 4d ago Divergent impacts of explainable AI for dermatological diagnosis on clinicians versus lay people Machine learning : nature.com subject feeds · 4d ago Alexander Rakhlin named director of the MIT Statistics and Data Science Center MIT News - Artificial intelligence · 4d ago Alexander Rakhlin named director of the MIT Statistics and Data Science Center MIT News - Machine learning · 4d ago Orchard: An open framework for scalable agentic AI Microsoft Research · 4d ago Why the Legendary Erdős Problems Are Falling to AI Quanta Magazine · 4d ago Topology-Aware Data Movement for Disaggregated GPU Inference cs.LG updates on arXiv.org · 5d ago Sensitivity Analysis of GRU, LSTM and Transformer Encoder in Classification of Automated Driving Systems cs.LG updates on arXiv.org · 5d ago Guarantees on Dynamical System Distinguishability for LLM Token Generation cs.LG updates on arXiv.org · 5d ago LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment cs.LG updates on arXiv.org · 5d ago Hierarchical Copula-Gumbel-Top-\texorpdfstring{$K$}{K} Routing: Two-Sided Dependence Control for Frozen Mixture-of-Experts at Fixed Per-Token Routing Laws cs.LG updates on arXiv.org · 5d ago LAWFUL: Law-Aligned Witness for Faithful Use of Latents cs.LG updates on arXiv.org · 5d ago MPP-GNN: Subject-Adaptive Community Detection for fMRI-Based Alzheimer's Disease Classification cs.LG updates on arXiv.org · 5d ago Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions cs.LG updates on arXiv.org · 5d ago SEDR-Seq2P: A Lightweight Dilated Residual Sequence-to-Point Network for Multi-Task Industrial NILM cs.LG updates on arXiv.org · 5d ago Predicting Steel Fatigue Life from Micrographs Using Physics-Informed Deep Learning cs.LG updates on arXiv.org · 5d ago Mitigating Class-Tail Undercoverage in Medical Vision-Language Models under Clinical Shift cs.LG updates on arXiv.org · 5d ago Flow Matching with Missing Data cs.LG updates on arXiv.org · 5d ago MMFGU: Multimodal Federated Graph Unlearning cs.LG updates on arXiv.org · 5d ago Mirror Learning cs.LG updates on arXiv.org · 5d ago TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning cs.LG updates on arXiv.org · 5d ago Feature Interaction Modeling for Physics-Informed Neural Networks and Neural Operators cs.LG updates on arXiv.org · 5d ago Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation cs.LG updates on arXiv.org · 5d ago Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations cs.LG updates on arXiv.org · 5d ago Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity cs.LG updates on arXiv.org · 5d ago An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks cs.LG updates on arXiv.org · 5d ago Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs stat.ML updates on arXiv.org · 5d ago Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression stat.ML updates on arXiv.org · 5d ago Structured Neural Chaos: An Adaptive Surrogate Modeling Framework for Functional Uncertainty Quantification and Global Sensitivity Analysis stat.ML updates on arXiv.org · 5d ago Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization stat.ML updates on arXiv.org · 5d ago Simple-regret rates and minimax optimality of fixed-prior expected improvement in Mat\'ern and squared-exponential RKHSs stat.ML updates on arXiv.org · 5d ago The Greedy Advantage in Finite-Horizon Bandits stat.ML updates on arXiv.org · 5d ago Analytical and Bootstrap Confidence Intervals of Double Machine Learning: Simulation studies and an application to rural-urban difference in obesity prevalence stat.ML updates on arXiv.org · 5d ago WaiT for the Signal: Simple Frequency-Aware Flow-Matching stat.ML updates on arXiv.org · 5d ago Bayesian Mediation Analysis for Individualized Treatment Rules stat.ML updates on arXiv.org · 5d ago Seeing the Forest for the Trees: The Gaussian Process Limit of BART stat.ML updates on arXiv.org · 5d ago The Debiased Score Test: Hunt-and-test for Semiparametric Hypotheses stat.ML updates on arXiv.org · 5d ago Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design stat.ML updates on arXiv.org · 5d ago Distance Profile Embedding for Independence and Conditional Independence Testing of Random Objects stat.ML updates on arXiv.org · 5d ago A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-Making and Evaluation stat.ML updates on arXiv.org · 5d ago Bayesian fusion forests for heterogeneous treatment effects on survival from randomised and real-world data stat.ML updates on arXiv.org · 5d ago Longitudinal Adaptive Experimental Design for Learning Multiple Target Estimands with Semiparametric Efficient Inference stat.ML updates on arXiv.org · 5d ago TerraNova: A Foundation Model for the Anthropocene stat.ML updates on arXiv.org · 5d ago Exponential Capacity in Multilayer Hetero-Associative Neural Networks stat.ML updates on arXiv.org · 5d ago When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning stat.ML updates on arXiv.org · 5d ago Differentially Private Nonparametric Modal Learning with Applications to Regression and Clustering stat.ML updates on arXiv.org · 5d ago Automatic report-based assessment of radiology-pathology concordance in surgical patients using BERT and DPCNN Machine learning : nature.com subject feeds · 5d ago Want to get more from AI? Treat every prompt like an experiment Machine learning : nature.com subject feeds · 5d ago A foundation model for sleep-based risk stratification and clinical outcomes Machine learning : nature.com subject feeds · 5d ago Understanding Alignment in Multimodal LLMs: A Comprehensive Study Apple Machine Learning Research · 5d ago Dynamic feature pyramid network for real-time gesture recognition Machine learning : nature.com subject feeds · 7d ago Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer Machine learning : nature.com subject feeds · 7d ago Is AI Reasoning Right for the Wrong Reasons? Quanta Magazine · 7d ago Tracing distinctive language in AI-written text Ai2 Blog · 8d ago Recursive transformers for semiconductor thermo-mechanical reliability cs.LG updates on arXiv.org · 8d ago Regularizing modality contribution drift in multimodal continual learning cs.LG updates on arXiv.org · 8d ago DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series cs.LG updates on arXiv.org · 8d ago PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective cs.LG updates on arXiv.org · 8d ago Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding cs.LG updates on arXiv.org · 8d ago RLPF: Reinforcement Learning from Performance Feedback for Code Generation cs.LG updates on arXiv.org · 8d ago SDO: Structure-Aware Data Organization for Efficient LLM Post-Training cs.LG updates on arXiv.org · 8d ago Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision cs.LG updates on arXiv.org · 8d ago Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents cs.LG updates on arXiv.org · 8d ago The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models cs.LG updates on arXiv.org · 8d ago Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance cs.LG updates on arXiv.org · 8d ago TIER-MoE: Trust-Informed Expert Routing via Conditional Modality Risk for Multimodal Fusion in Biomedical Classification cs.LG updates on arXiv.org · 8d ago EvoCause: LLM-Guided Evolution of Causal Graphs for Root Cause Analysis cs.LG updates on arXiv.org · 8d ago THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model cs.LG updates on arXiv.org · 8d ago Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models cs.LG updates on arXiv.org · 8d ago ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution cs.LG updates on arXiv.org · 8d ago Modeling Decisions in Blockchain Analytics: A Leakage-Aware Evaluation of Tree-Based vs. Sequential Models cs.LG updates on arXiv.org · 8d ago Compression-Based Behavioral Similarity for Open-World Sybil Discovery on Ethereum cs.LG updates on arXiv.org · 8d ago Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation cs.LG updates on arXiv.org · 8d ago The Convergence Behavior of Adam under Heavy-Tailed Noise cs.LG updates on arXiv.org · 8d ago More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility stat.ML updates on arXiv.org · 8d ago Expected Survival-Time Bounds for Robust Optimization Over Time under Isotropic Gaussian Dynamics stat.ML updates on arXiv.org · 8d ago An analysis of binary isotonic regression: degrees of freedom and implications for calibration stat.ML updates on arXiv.org · 8d ago HOMER: Huber-of-Means for Efficient and Robust Estimation in Hilbert Spaces stat.ML updates on arXiv.org · 8d ago Robust Wavelength Selection for Partial Least Squares Sugar Content Estimation Using Combinatorial Bayesian Optimization stat.ML updates on arXiv.org · 8d ago Error Analysis of Neural-Network-Based Engression stat.ML updates on arXiv.org · 8d ago Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy stat.ML updates on arXiv.org · 8d ago Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators stat.ML updates on arXiv.org · 8d ago On a joint simultaneous learning of relevant feature subsets and subspaces in regression-like problems stat.ML updates on arXiv.org · 8d ago Uncertainty quantification for trustworthy deep learning: Methods and measures stat.ML updates on arXiv.org · 8d ago Doubly Robust Functional Representation Learning for Longitudinal Causal Inference with Irregular Histories stat.ML updates on arXiv.org · 8d ago Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision stat.ML updates on arXiv.org · 8d ago THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model stat.ML updates on arXiv.org · 8d ago Adaptive Nystr\"om for Gaussian Process Regression stat.ML updates on arXiv.org · 8d ago Entropy-Smooth Convex Optimization Cannot Be Accelerated stat.ML updates on arXiv.org · 8d ago Strategies for Milestone-driven Start-ups in Multi-activity Settings stat.ML updates on arXiv.org · 8d ago Scalable Graph Coreset Selection via Greedy Sampling stat.ML updates on arXiv.org · 8d ago A Mathematical Framework for Topological Causal Data Analysis stat.ML updates on arXiv.org · 8d ago Non-partitioned e-detectors for nonparametric sequential change detection stat.ML updates on arXiv.org · 8d ago Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata stat.ML updates on arXiv.org · 8d ago Unify learns cellular evolution with universal multimodal embeddings Machine learning : nature.com subject feeds · 8d ago Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms Machine learning : nature.com subject feeds · 8d ago Learning from routine health system data builds better neuroimaging AI models Machine learning : nature.com subject feeds · 8d ago A machine learning framework for predicting and modulating condition-dependent protein phase separation Machine learning : nature.com subject feeds · 8d ago Scientists using LLMs will ‘do more, less well’, modelling study predicts Machine learning : nature.com subject feeds · 8d ago Continual integration of single-cell multimodal data with MIRACLE Machine learning : nature.com subject feeds · 8d ago CellTune: an integrative software for accurate cell classification in spatial proteomics Machine learning : nature.com subject feeds · 8d ago Daniela Rus receives Bavarian Minister-President's High-Tech Prize MIT News - Artificial intelligence · 8d ago Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence The latest research from Google · 8d ago Connecting research to policy on Capitol Hill MIT News - Artificial intelligence · 8d ago How controllers from industrial machinery can coordinate multitask machine learning Amazon Science homepage · 8d ago Echoverse: Deep, evolving environments for computer-use agents Microsoft Research · 8d ago EvoLib: Turning experience into evolving knowledge Microsoft Research · 8d ago Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration Google DeepMind News · 8d ago Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning cs.LG updates on arXiv.org · 9d ago Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football cs.LG updates on arXiv.org · 9d ago Meta-Learned Reward Shaping for Reinforcement Learning from Human Feedback cs.LG updates on arXiv.org · 9d ago Data Fusion and Contrastive Alignment for Unconstrained IR Molecular Structure Elucidation cs.LG updates on arXiv.org · 9d ago Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models cs.LG updates on arXiv.org · 9d ago Dynamic Parameterization Is Not Dynamic Inference cs.LG updates on arXiv.org · 9d ago Weak-to-Strong On-Policy Distillation cs.LG updates on arXiv.org · 9d ago Between Gradient and Natural Gradient: A Continuum of LoRA Initializations cs.LG updates on arXiv.org · 9d ago Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR cs.LG updates on arXiv.org · 9d ago Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection cs.LG updates on arXiv.org · 9d ago FloDR: An invertible dimensionality reduction method based on a normalising flow cs.LG updates on arXiv.org · 9d ago Entity Resolution in Practice: Lessons from a Self-Serve Pipeline cs.LG updates on arXiv.org · 9d ago Learning Implicit Causal World Models from Multi-Agent Demonstrations cs.LG updates on arXiv.org · 9d ago RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning cs.LG updates on arXiv.org · 9d ago Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks cs.LG updates on arXiv.org · 9d ago MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts cs.LG updates on arXiv.org · 9d ago High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumption cs.LG updates on arXiv.org · 9d ago Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning cs.LG updates on arXiv.org · 9d ago ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling cs.LG updates on arXiv.org · 9d ago Q-Steer: Action-Value Guidance for Molecular Policy Optimization cs.LG updates on arXiv.org · 9d ago When Kernel Ridge Regression Meets the H\"older-Zygmund Class: Minimax Optimality and Failure of Properness stat.ML updates on arXiv.org · 9d ago Origins and mitigation of double descent in reduced order modeling stat.ML updates on arXiv.org · 9d ago Chaos Is a LADDER: Domain Generalization Beyond Invariance via Reweighting stat.ML updates on arXiv.org · 9d ago Early Failure Prediction from Near-Anomaly Detection: A Proactive Approach stat.ML updates on arXiv.org · 9d ago Crossing-Free Probabilistic K-Line Forecasts Without Retraining stat.ML updates on arXiv.org · 9d ago Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents stat.ML updates on arXiv.org · 9d ago Conformalized Rate-Adaptive Sensing stat.ML updates on arXiv.org · 9d ago Breaking the Curse with BAND: Nonparametric Distribution Estimation in High Dimensions stat.ML updates on arXiv.org · 9d ago Feature Bagging Provides Stability stat.ML updates on arXiv.org · 9d ago PIKS: Universal Physics-Informed Kernel Methods stat.ML updates on arXiv.org · 9d ago Randomizing the Number of Centers in k-means++ stat.ML updates on arXiv.org · 9d ago Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection stat.ML updates on arXiv.org · 9d ago Denoising growth complexity: Data geometry and certified schedules for diffusion sampling stat.ML updates on arXiv.org · 9d ago The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text stat.ML updates on arXiv.org · 9d ago Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning stat.ML updates on arXiv.org · 9d ago High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumption stat.ML updates on arXiv.org · 9d ago Existence-Field Diffusion Model for Spatial Point Processes with Variable Cardinality stat.ML updates on arXiv.org · 9d ago Universality and Approximation Rates of Graph Neural Networks with Random Features stat.ML updates on arXiv.org · 9d ago Compactly supported radial basis functions as probability density functions stat.ML updates on arXiv.org · 9d ago BayesAME: Bayesian Active Model Evaluation stat.ML updates on arXiv.org · 9d ago Structural alignments to design functional RNAs Machine learning : nature.com subject feeds · 9d ago An embedding-based framework enables statistical testing of gene-set function hypotheses inferred by large language models Machine learning : nature.com subject feeds · 9d ago Dimensionality Reduction Meets Network Science: Sensemaking on UMAP’s kNN Graph Apple Machine Learning Research · 9d ago MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization Apple Machine Learning Research · 9d ago We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control Google DeepMind News · 9d ago A new benchmark for evaluating patient-facing health AI agents Amazon Science homepage · 9d ago How a medical database developed at MIT evolved into a global standard of data-sharing MIT News - Artificial intelligence · 9d ago From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon The Berkeley Artificial Intelligence Research Blog · 10d ago FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting cs.LG updates on arXiv.org · 10d ago Human Preference aligned Tabular Similarity cs.LG updates on arXiv.org · 10d ago Behavior-Driven Explainability cs.LG updates on arXiv.org · 10d ago Eliminating Propagation Delay: Attention-Based Spatial-Temporal Fusion Graph Convolution Network for Traffic Flow Prediction cs.LG updates on arXiv.org · 10d ago Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension cs.LG updates on arXiv.org · 10d ago GAUGE: Grading Agent-Built Financial Models Without a Golden Answer cs.LG updates on arXiv.org · 10d ago LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models cs.LG updates on arXiv.org · 10d ago Inverse RL Helps Align AI by Imitating Humans cs.LG updates on arXiv.org · 10d ago Multiclass Classification without Labels via Posterior Simplex Geometry cs.LG updates on arXiv.org · 10d ago Stable FP4 Training via Transposition-Invariant Block Quantization cs.LG updates on arXiv.org · 10d ago Generative Distributionally Robust Optimization cs.LG updates on arXiv.org · 10d ago Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning cs.LG updates on arXiv.org · 10d ago Conformal Cascade: Distribution-Free Accuracy Guarantees for Multi-Tier LLM Inference cs.LG updates on arXiv.org · 10d ago Lantern: Conflict-Aware Gradient Blending for Physics-Guided Diffusion Models in Calorimeter Simulation cs.LG updates on arXiv.org · 10d ago Score-Based Stabilization for Time-Dependent Problems cs.LG updates on arXiv.org · 10d ago Semantic Space Search Trajectory Networks cs.LG updates on arXiv.org · 10d ago Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning cs.LG updates on arXiv.org · 10d ago Interpretable GOHR Agents via Sparse Autoencoders cs.LG updates on arXiv.org · 10d ago Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility cs.LG updates on arXiv.org · 10d ago Accurate structural modeling of chemically diverse molecular interfaces with Vilya-2 cs.LG updates on arXiv.org · 10d ago Lloyd's $K$-Means Clustering Algorithm Is Frank-Wolfe in Disguise stat.ML updates on arXiv.org · 10d ago Learning from the Unseen: Offline Reinforcement Learning with Hidden Actions stat.ML updates on arXiv.org · 10d ago Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields? stat.ML updates on arXiv.org · 10d ago A Generalized Tangent Approximation based Variational Inference Framework for Strongly Super-Gaussian Likelihoods stat.ML updates on arXiv.org · 10d ago Multiclass Classification without Labels via Posterior Simplex Geometry stat.ML updates on arXiv.org · 10d ago Generative Distributionally Robust Optimization stat.ML updates on arXiv.org · 10d ago Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation stat.ML updates on arXiv.org · 10d ago Transfer Learning in High-Dimensional Clustering: Minimax Thresholds and Applications in Single-Cell Data stat.ML updates on arXiv.org · 10d ago Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method stat.ML updates on arXiv.org · 10d ago Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks stat.ML updates on arXiv.org · 10d ago Sequential Preconditioned Conjugate Gradient Method for Linear Statistical Models stat.ML updates on arXiv.org · 10d ago Contextual Deconvolution for Variance-Stable Demand Sensing: Kernel-Modulated Operators in Promotional Retail stat.ML updates on arXiv.org · 10d ago Generalised Robust Bayes for Joint Inference of Model and Contamination stat.ML updates on arXiv.org · 10d ago Bias-corrected Cox regression with AI-extracted covariates via calibration summary statistics stat.ML updates on arXiv.org · 10d ago The Barron-Lipschitz Energy Gap and Depth Separation Phenomena in Scientific Machine Learning stat.ML updates on arXiv.org · 10d ago Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm stat.ML updates on arXiv.org · 10d ago Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance stat.ML updates on arXiv.org · 10d ago On the Convergence Analysis of Muon stat.ML updates on arXiv.org · 10d ago TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models stat.ML updates on arXiv.org · 10d ago Extreme Event Aware ($\eta$-) Learning stat.ML updates on arXiv.org · 10d ago Gemini Robotics 2 brings whole body intelligence to robots Google DeepMind News · 10d ago The OlmoEarth Platform: Geospatial inference at planetary scale Ai2 Blog · 11d ago Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B cs.LG updates on arXiv.org · 11d ago CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents cs.LG updates on arXiv.org · 11d ago CausalGate: Causal Importance Distillation for Transformer Module Pruning cs.LG updates on arXiv.org · 11d ago Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks cs.LG updates on arXiv.org · 11d ago QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation cs.LG updates on arXiv.org · 11d ago Learning to Access Computation: Accessibility Plasticity as a Principle of Adaptive Intelligence cs.LG updates on arXiv.org · 11d ago Hierarchical Grading in Large Language Models cs.LG updates on arXiv.org · 11d ago An Integrated Deep Learning and Statistical Framework for Whole-Network Gene--Environment Association with Leaf Vascular Architecture cs.LG updates on arXiv.org · 11d ago Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation cs.LG updates on arXiv.org · 11d ago DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning cs.LG updates on arXiv.org · 11d ago Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement cs.LG updates on arXiv.org · 11d ago CC-AOS: Cost- and Horizon-Conditioned Amortized Backward Induction for Finite-Horizon Optimal Stopping cs.LG updates on arXiv.org · 11d ago Predicting the Outcome of rTMS Depression Therapy using EEG Signals and CNN cs.LG updates on arXiv.org · 11d ago LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning cs.LG updates on arXiv.org · 11d ago Multimodal Surface EMG Hand Gesture Recognition Using Query-Based Transformers for Prosthetic Control cs.LG updates on arXiv.org · 11d ago What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation cs.LG updates on arXiv.org · 11d ago Optimizing Transformer Neural Network for Real-Time Outlier Detection on FPGAs cs.LG updates on arXiv.org · 11d ago FMOPF: Latent Flow Matching with Constraint-Aware Interaction Priors for AC Optimal Power Flow cs.LG updates on arXiv.org · 11d ago Multimodal Domain Generalization for Depression Detection: An Attention-Based BiLSTM Network with Domain-Adversarial Training cs.LG updates on arXiv.org · 11d ago Physically Verifiable Evidence and LLM-Based Reporting for Bearing Fault Diagnosis cs.LG updates on arXiv.org · 11d ago TLRNet: Estimating Individual Treatment Effect based on Local Information and Single Learner Structure stat.ML updates on arXiv.org · 11d ago Amortized Bayesian Causal Discovery of Extended Factor Graphs stat.ML updates on arXiv.org · 11d ago Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model stat.ML updates on arXiv.org · 11d ago Variable Importance Identification Through Lazy Training for Binary Classification stat.ML updates on arXiv.org · 11d ago Robust Conformalized Selection with Noisy Responses stat.ML updates on arXiv.org · 11d ago Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities stat.ML updates on arXiv.org · 11d ago Operator Neural Jump ODEs: $L^2$-optimal prediction in function spaces stat.ML updates on arXiv.org · 11d ago Adaptive Multi-Scale Forecasting and Gate-Localized Conformal Prediction for Multivariate Nonstationary Time Series stat.ML updates on arXiv.org · 11d ago Beyond ICA: Identifiability by Symmetry Breaking stat.ML updates on arXiv.org · 11d ago FedSLIM: Privacy-Preserving Federated MDL-Based Descriptive Pattern Mining Across Data Silos stat.ML updates on arXiv.org · 11d ago Learning Asymptotics with Convergence-Rate Guarantees using Linear Least Squares stat.ML updates on arXiv.org · 11d ago Context-Adaptive Inference: A Unified Statistical and Foundation-Model View stat.ML updates on arXiv.org · 11d ago Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data stat.ML updates on arXiv.org · 11d ago Two-Timescale Hierarchical Reinforcement Learning for Resilient Operations stat.ML updates on arXiv.org · 11d ago Learning switched non-linear dynamical systems from a single trajectory stat.ML updates on arXiv.org · 11d ago Distributional Split Criteria for Random Forests: Extensions, Shrinkage, and the Robustness of Mean Splitting stat.ML updates on arXiv.org · 11d ago On Non-Stationary Dynamic Pricing: Adaptivity and Optimality stat.ML updates on arXiv.org · 11d ago Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD stat.ML updates on arXiv.org · 11d ago proxymate: Diagnosis and Adjustment of Proxy Estimates for Reliable Inference stat.ML updates on arXiv.org · 11d ago Frequency-Based Reservoir computing stat.ML updates on arXiv.org · 11d ago Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers Apple Machine Learning Research · 11d ago Cloud-Native Evaluation-as-a-Service: A Microservices Architecture for Scalable AI Monitoring with Conformal Guarantees cs.LG updates on arXiv.org · 12d ago On the Depth Scalability of Logic Gate Networks cs.LG updates on arXiv.org · 12d ago MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion cs.LG updates on arXiv.org · 12d ago Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions cs.LG updates on arXiv.org · 12d ago Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models cs.LG updates on arXiv.org · 12d ago Quasi-Monte Carlo Initialization for Meta-Reinforcement Learning cs.LG updates on arXiv.org · 12d ago Toward Goal-Agnostic Joint-Embedding Predictive Control of Partial Differential Equations cs.LG updates on arXiv.org · 12d ago Multi-Horizon Consistency as Geometry: When Latent Dynamics Contract, and When They Do Not cs.LG updates on arXiv.org · 12d ago Adjustment Speed as a Safety Constraint for Nonstationary Reinforcement Learning cs.LG updates on arXiv.org · 12d ago A Drift Stable Quantum Federated Learning for Intelligent Services cs.LG updates on arXiv.org · 12d ago Shallower ReLU Network Representations via Exact Linear Algebra cs.LG updates on arXiv.org · 12d ago Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning cs.LG updates on arXiv.org · 12d ago Physically Constrained Federated Additive Models for O-RAN SLA-Risk Prediction cs.LG updates on arXiv.org · 12d ago Neural Feature Governance: Extending Atom Prevalence cs.LG updates on arXiv.org · 12d ago Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration cs.LG updates on arXiv.org · 12d ago Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA cs.LG updates on arXiv.org · 12d ago CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecasting cs.LG updates on arXiv.org · 12d ago Learning What Matters: Supervising Sparse Attention Routing with Causal Evidence Sets cs.LG updates on arXiv.org · 12d ago An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning cs.LG updates on arXiv.org · 12d ago A Defense of the Quadratic Model cs.LG updates on arXiv.org · 12d ago Prior laundering: learned priors with inherited, undetectable overconfidence stat.ML updates on arXiv.org · 12d ago Simulation-Based Empirical Bayes stat.ML updates on arXiv.org · 12d ago Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes stat.ML updates on arXiv.org · 12d ago Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model stat.ML updates on arXiv.org · 12d ago Variational Low-rank Tensor Decomposition for Multisubject Spatiotemporal Data Analysis stat.ML updates on arXiv.org · 12d ago General Value Functions for Remaining Useful Life and Failure-Mode Prediction stat.ML updates on arXiv.org · 12d ago Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting stat.ML updates on arXiv.org · 12d ago Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks stat.ML updates on arXiv.org · 12d ago Learning Ergodic Dynamical Systems from a Finite Trajectory stat.ML updates on arXiv.org · 12d ago Graph-Based Correlation Matrix Generation: A Convex Optimization Approach stat.ML updates on arXiv.org · 12d ago CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference stat.ML updates on arXiv.org · 12d ago Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration stat.ML updates on arXiv.org · 12d ago An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning stat.ML updates on arXiv.org · 12d ago A Defense of the Quadratic Model stat.ML updates on arXiv.org · 12d ago Longitudinal Random Forests for Sparse and Irregular Response Trajectories stat.ML updates on arXiv.org · 12d ago Reconstruction of Enhanced Causal Omnidirectional Network (RECON) stat.ML updates on arXiv.org · 12d ago Toward High-Fidelity 3D Point-Cloud Learning for Brain Folding Morphology Prediction Using Trans-Unet stat.ML updates on arXiv.org · 12d ago Distributional Determinantal Point Process for Repulsive Clustering of Distributions stat.ML updates on arXiv.org · 12d ago Scaling Laws for Classical Machine Learning on Tabular Data: A Benchmark Study stat.ML updates on arXiv.org · 12d ago From Score Approximation to Distribution Approximation in Score-Based Diffusion Models stat.ML updates on arXiv.org · 12d ago Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction The Berkeley Artificial Intelligence Research Blog · 13d ago Amazon is investing in the Lean Focused Research Organization Amazon Science homepage · 13d ago Who gets to understand AI? Ai2 Blog · 15d ago DataPrep-Bench: Benchmarking LLMs as Training Data Preparators cs.LG updates on arXiv.org · 15d ago PhantomFill: When the Form Demands an Answer, Language Models Invent One cs.LG updates on arXiv.org · 15d ago The Active Ingredient in Muon's Grokking cs.LG updates on arXiv.org · 15d ago Scaling Closed-Loop Feature Channel Configuration with LLMs cs.LG updates on arXiv.org · 15d ago Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs cs.LG updates on arXiv.org · 15d ago Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts cs.LG updates on arXiv.org · 15d ago Generative Bayesian Filtering for State Estimation cs.LG updates on arXiv.org · 15d ago Do Active SAE Feature Planes Carry More Holonomy? A Preregistered Reversal in Gemma cs.LG updates on arXiv.org · 15d ago Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement cs.LG updates on arXiv.org · 15d ago CLOE: Christoffel Loss Autoencoder for Anomaly Detection cs.LG updates on arXiv.org · 15d ago Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development cs.LG updates on arXiv.org · 15d ago Grounding Investor Views: Neural Predicates in the Black-Litterman Model cs.LG updates on arXiv.org · 15d ago A Graph Neural Network approach to zero-shot Digital Twins cs.LG updates on arXiv.org · 15d ago ReliableTableQA:How Much Supervision Does Reliability Annotation Need? cs.LG updates on arXiv.org · 15d ago Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches cs.LG updates on arXiv.org · 15d ago Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling cs.LG updates on arXiv.org · 15d ago From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime cs.LG updates on arXiv.org · 15d ago HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws cs.LG updates on arXiv.org · 15d ago Improving Access to Essential Medicines via Decision-Aware Machine Learning cs.LG updates on arXiv.org · 15d ago When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion cs.LG updates on arXiv.org · 15d ago SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting stat.ML updates on arXiv.org · 15d ago Automatic knot selection in smooth additive models stat.ML updates on arXiv.org · 15d ago Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting stat.ML updates on arXiv.org · 15d ago Generative Bayesian Filtering for State Estimation stat.ML updates on arXiv.org · 15d ago ConfidenceBench: Evaluating Confidence Calibration in Large Language Models stat.ML updates on arXiv.org · 15d ago CLOE: Christoffel Loss Autoencoder for Anomaly Detection stat.ML updates on arXiv.org · 15d ago Fisher Widths: Local Learning Geometry and Anisotropic Recovery stat.ML updates on arXiv.org · 15d ago When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers stat.ML updates on arXiv.org · 15d ago High Minima of Gaussian Processes: Overshoots and Minimizer Locations stat.ML updates on arXiv.org · 15d ago Twoblock clustering trees with coskewness-based dimension reduction: recovering piecewise multivariate linear regimes stat.ML updates on arXiv.org · 15d ago Self-Balancing Sequential Sampling: Fast Convergence with Controlled Predictability stat.ML updates on arXiv.org · 15d ago Smooth Neural Point Processes via B-Splines stat.ML updates on arXiv.org · 15d ago Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks stat.ML updates on arXiv.org · 15d ago Cautious optimism for deep parameterized quantum circuits stat.ML updates on arXiv.org · 15d ago Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking stat.ML updates on arXiv.org · 15d ago Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design stat.ML updates on arXiv.org · 15d ago Optimal use of a black-box learner in semiparametric estimation stat.ML updates on arXiv.org · 15d ago Zero-Flow Two-Sample Tests stat.ML updates on arXiv.org · 15d ago Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana stat.ML updates on arXiv.org · 15d ago Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning stat.ML updates on arXiv.org · 15d ago Working to automate nuclear plant operations MIT News - Artificial intelligence · 15d ago MIT projects selected for funding under US Department of Energy’s Genesis Mission MIT News - Artificial intelligence · 16d ago Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions cs.LG updates on arXiv.org · 16d ago Bayesian Wind Tunnels for Model Selection cs.LG updates on arXiv.org · 16d ago CruiseBench: A Real-Flight-Aligned N-CMAPSS Benchmark for Engine RUL Prediction cs.LG updates on arXiv.org · 16d ago Air Quality Arena: A Large-Scale Multi-Region Ground Monitoring Dataset and Benchmark for Air Quality Forecasting with Time-Series Foundation Models cs.LG updates on arXiv.org · 16d ago Challenges of Explainability in Continual Learning for Time Series Forecasting cs.LG updates on arXiv.org · 16d ago SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning cs.LG updates on arXiv.org · 16d ago STN-TGAT: Top-K Portfolio Construction via Prior-Guided Graph Attention with Learnable Soft-Threshold Sparsification cs.LG updates on arXiv.org · 16d ago Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance cs.LG updates on arXiv.org · 16d ago Scale-Aware Learning of Chaotic Dynamics on Unstructured Meshes via Binned Spectral Losses cs.LG updates on arXiv.org · 16d ago Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation cs.LG updates on arXiv.org · 16d ago The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory cs.LG updates on arXiv.org · 16d ago LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning cs.LG updates on arXiv.org · 16d ago Predicting Groundwater Arsenic Concentrations Using Graph Neural Networks cs.LG updates on arXiv.org · 16d ago Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks cs.LG updates on arXiv.org · 16d ago Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning cs.LG updates on arXiv.org · 16d ago From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation cs.LG updates on arXiv.org · 16d ago Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning cs.LG updates on arXiv.org · 16d ago Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models cs.LG updates on arXiv.org · 16d ago Predictive single cell foundation model for gene regulation and aging with privacy-preserving tabular learning cs.LG updates on arXiv.org · 16d ago When Does Consensus Beat Voting? A Critical Analysis of Statistical Label Fusion in Medical Image Segmentation cs.LG updates on arXiv.org · 16d ago A Bayesian Framework for Built-in Input Dimension Reduction for Gaussian Process Modeling stat.ML updates on arXiv.org · 16d ago Boltzmann-Expected Molecular Design with Decoupled Annealing Flows stat.ML updates on arXiv.org · 16d ago RELTA-SGLD: Relative-Growth Localized Taming for Nonconvex Stochastic-Gradient Langevin Learning stat.ML updates on arXiv.org · 16d ago Optimal Recalibration of an Online Predictor stat.ML updates on arXiv.org · 16d ago Data-Poisoning Audits for Causal Effect Estimation stat.ML updates on arXiv.org · 16d ago Non--negative matrix factorization using the \textit{R} package \textsf{nnmf} stat.ML updates on arXiv.org · 16d ago Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparison stat.ML updates on arXiv.org · 16d ago Statistical Inference for Rank Allocation in Low-Rank Adaptation stat.ML updates on arXiv.org · 16d ago Adaptive Bayesian Online Learning via Expert Aggregation stat.ML updates on arXiv.org · 16d ago Adaptive deep nonparametric regression from dependent data under covariate shift stat.ML updates on arXiv.org · 16d ago Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions stat.ML updates on arXiv.org · 16d ago Bayesian Wind Tunnels for Model Selection stat.ML updates on arXiv.org · 16d ago Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics stat.ML updates on arXiv.org · 16d ago Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines stat.ML updates on arXiv.org · 16d ago Total Variation Distance Estimation in Autoregressive Models stat.ML updates on arXiv.org · 16d ago Deep Shape Regression for Planar Curves with Multimodal Covariates stat.ML updates on arXiv.org · 16d ago Efficient Clustering with Provable Guardrails for LLM Inference at Scale stat.ML updates on arXiv.org · 16d ago Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence stat.ML updates on arXiv.org · 16d ago Active Inference as a Convex Markov Decision Process stat.ML updates on arXiv.org · 16d ago Quantum Kernels and the Cross-Section of Stock Returns: Anatomy of a Vanishing Advantage stat.ML updates on arXiv.org · 16d ago SymptomAI: Towards a conversational AI agent for everyday symptom assessment The latest research from Google · 16d ago Towards a quantum computer that learns from its errors The latest research from Google · 16d ago Professor Emeritus Dimitri Bertsekas, influential computer scientist and prolific author, dies at 83 MIT News - Artificial intelligence · 16d ago Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission Google DeepMind News · 16d ago FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration cs.LG updates on arXiv.org · 17d ago Beyond Output-Space Calibration: Spectral Evidence Bundling for Selective Reliability Estimation in Time-Series Classification cs.LG updates on arXiv.org · 17d ago Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models cs.LG updates on arXiv.org · 17d ago ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian Optimization cs.LG updates on arXiv.org · 17d ago FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images cs.LG updates on arXiv.org · 17d ago Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression cs.LG updates on arXiv.org · 17d ago Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring cs.LG updates on arXiv.org · 17d ago Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority cs.LG updates on arXiv.org · 17d ago BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop cs.LG updates on arXiv.org · 17d ago Multi-Timescale Latent-Action DRL for Joint Optimization in Edge-Cloud Networks cs.LG updates on arXiv.org · 17d ago Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios cs.LG updates on arXiv.org · 17d ago SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions cs.LG updates on arXiv.org · 17d ago Dual-domain fused LSTM modeling for efficient time-dependent reliability analysis cs.LG updates on arXiv.org · 17d ago Reliability Scales Inversely: Bigger Models Compound Mistakes Faster via a Hidden Auto-Regressive Risk Regime cs.LG updates on arXiv.org · 17d ago One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context cs.LG updates on arXiv.org · 17d ago Uncertainty Quantification for AI-Driven Crash Simulation Surrogates: A Comparative Study of Monte Carlo Dropout and Deep Ensemble on Open-Source Bumper Beam Benchmark cs.LG updates on arXiv.org · 17d ago On the Limits of Support-Preserving Alignment and Bounded Filtering cs.LG updates on arXiv.org · 17d ago A Better Start for Language Models: Domain-Conditional Position Offsets cs.LG updates on arXiv.org · 17d ago TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue cs.LG updates on arXiv.org · 17d ago The Information Shadow: Measuring Structural Limits on What Language Models Can Learn cs.LG updates on arXiv.org · 17d ago Disentangling Forced and Internal Climate Variability in Single Realizations using Dynamic Mode Decomposition with Control stat.ML updates on arXiv.org · 17d ago Mixing-Free and Signal-Optimal Learning of Gaussian Graphical Models from Glauber Dynamics stat.ML updates on arXiv.org · 17d ago The Price of Hidden Curvature: An $\widetilde{\Omega} (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization stat.ML updates on arXiv.org · 17d ago Algebraic Signatures for Structural Learning in Probability Tensors stat.ML updates on arXiv.org · 17d ago The Tractability Landscape of Sampling with Inexact Scores stat.ML updates on arXiv.org · 17d ago Fundamental limits of distributed multiclass classification from simple binary decisions stat.ML updates on arXiv.org · 17d ago PAC--Bayes Bounds on Quotient Parameter Spaces: Geometry-induced Implicit-Bias Priors stat.ML updates on arXiv.org · 17d ago Using binary silver labels in electronic health records-based computable phenotyping algorithms stat.ML updates on arXiv.org · 17d ago Uncertainty quantification in mechanics: A unified Bayesian perspective stat.ML updates on arXiv.org · 17d ago Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posterior stat.ML updates on arXiv.org · 17d ago Optimizing Regret stat.ML updates on arXiv.org · 17d ago Deep learning-based prediction of time-resolved adhesive forces in viscoelastic Hertzian contacts stat.ML updates on arXiv.org · 17d ago On the sensitivity of machine-learned probabilistic weather forecast models to scale-aware scoring rules stat.ML updates on arXiv.org · 17d ago Boundary-Adapted PINNs for Elliptic Dirichlet Problems: $H^2(\Omega)$ A Priori Error Bounds with Application to Mean Escape Time Computation stat.ML updates on arXiv.org · 17d ago Some cautionary tales about Bayesian predictive inference stat.ML updates on arXiv.org · 17d ago Provable diffusion-based posterior sampling for linear inverse problems via DDIM stat.ML updates on arXiv.org · 17d ago Generalized Least Squares Kernelized Tensor Factorization stat.ML updates on arXiv.org · 17d ago Low-Rank Evolutionary Deep Neural Networks via Adaptive Tangent-Space Reduction stat.ML updates on arXiv.org · 17d ago Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber Google DeepMind News · 17d ago Reinforcement Learning-Guided NSGA-II Enhanced with Gray Relational Coefficient for Multi-Objective Optimization: Application to NASDAQ Portfolio Optimization cs.LG updates on arXiv.org · 18d ago DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth cs.LG updates on arXiv.org · 18d ago Fully-sensorized smart-eyewear platform for on-device Machine Learning cs.LG updates on arXiv.org · 18d ago LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats cs.LG updates on arXiv.org · 18d ago Operator-Aware Mixed-Precision Tolerance Calibration for Tensor Kernels cs.LG updates on arXiv.org · 18d ago RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce cs.LG updates on arXiv.org · 18d ago Orthogonal Gradient Constraints Shape Noisy-Label Memorization Dynamics cs.LG updates on arXiv.org · 18d ago From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language cs.LG updates on arXiv.org · 18d ago Token-Level Cross-Modal Transformer with Contrastive Multi-Task Learning for Breast Cancer Subtype Classification and Survival Prediction cs.LG updates on arXiv.org · 18d ago HantaWatch: Federated Learning for Hantavirus Genomic Surveillance cs.LG updates on arXiv.org · 18d ago OpenMHC: Accelerating the Science of Wearable Foundation Models cs.LG updates on arXiv.org · 18d ago The Failures of Marginal Influence-Based Attribution Methods for Global Time Series Explanations cs.LG updates on arXiv.org · 18d ago Quantizing Recursive Reasoning Models cs.LG updates on arXiv.org · 18d ago Diffusion-corrected Autoregressive Fourier Neural Operator for Droplet Evolution Prediction cs.LG updates on arXiv.org · 18d ago BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges cs.LG updates on arXiv.org · 18d ago Normalized Rewards for Preference Optimization cs.LG updates on arXiv.org · 18d ago KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch? cs.LG updates on arXiv.org · 18d ago TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment cs.LG updates on arXiv.org · 18d ago RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants cs.LG updates on arXiv.org · 18d ago CIGPO: Contextual Information-Gain Policy Optimization for Multi-Turn Evidence-Reading LLM Agents cs.LG updates on arXiv.org · 18d ago Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness stat.ML updates on arXiv.org · 18d ago MTSSL: Meta-Thresholding Semi-Supervised Learning stat.ML updates on arXiv.org · 18d ago Backpropagation-Free Trunk Training via the Split Forward Gradients stat.ML updates on arXiv.org · 18d ago Isotonic Conformal Prediction stat.ML updates on arXiv.org · 18d ago Semi-Supervised Conditional Diffusion via Label Augmentation stat.ML updates on arXiv.org · 18d ago A Causal Markov Condition for Value stat.ML updates on arXiv.org · 18d ago Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations stat.ML updates on arXiv.org · 18d ago Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets stat.ML updates on arXiv.org · 18d ago Deep Adaptive Bayesian Screening stat.ML updates on arXiv.org · 18d ago Twisted Schr\"odinger Bridge Matching stat.ML updates on arXiv.org · 18d ago Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning stat.ML updates on arXiv.org · 18d ago Kernel Regression with Tensor Trains and Hadamard Overparameterization stat.ML updates on arXiv.org · 18d ago Efficient Sequential Evaluation of Large Language Models stat.ML updates on arXiv.org · 18d ago An efficient adaptive dimension selection algorithm for multidimensional probit graded response models stat.ML updates on arXiv.org · 18d ago An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers stat.ML updates on arXiv.org · 18d ago COVAriance-Induced Fairness Gap Penalty for Subgroup-Fair Clustering stat.ML updates on arXiv.org · 18d ago Classification Trees with Valid Inference via the Exponential Mechanism stat.ML updates on arXiv.org · 18d ago Quantifying Ranking Uncertainty in LLM Benchmarks stat.ML updates on arXiv.org · 18d ago Reducing Per-Sample Harm in Stochastic Optimization stat.ML updates on arXiv.org · 18d ago Scaling Limits of Constant-Stepsize SGD at Flat Minima stat.ML updates on arXiv.org · 18d ago Structure of the Circular-Dyadic Convolution Error cs.LG updates on arXiv.org · 19d ago Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling cs.LG updates on arXiv.org · 19d ago A Transportable Threshold-Based Framework for Interpretable Classification of Medical Data cs.LG updates on arXiv.org · 19d ago Regularity-Aware Stochastic MGDA with Adaptive Conflict-Avoidant Update Direction Control cs.LG updates on arXiv.org · 19d ago AI Trading: Evaluating Large Language Models for Technical Market Analysis cs.LG updates on arXiv.org · 19d ago qZACH-ViT: Quantization-Aware Intrinsic Explanations with Recursive Attribution-Stabilized Optimization cs.LG updates on arXiv.org · 19d ago From hyperplanes to hyperellipsoids: characterizing the inherent interpretability of linear and single-qubit mixed-state binary classification models cs.LG updates on arXiv.org · 19d ago Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths cs.LG updates on arXiv.org · 19d ago Who Became Financially Vulnerable After COVID-19? A Population-Level Machine Learning Analysis Using MEPS Data cs.LG updates on arXiv.org · 19d ago LLM4EHR: Aligning Clinical Time Series with Medical Event Sequences via Large Language Models cs.LG updates on arXiv.org · 19d ago Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention cs.LG updates on arXiv.org · 19d ago Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers cs.LG updates on arXiv.org · 19d ago Robust Peak-cost Constrained Reinforcement Learning cs.LG updates on arXiv.org · 19d ago ADS-C: Antidistillation Sampling for Classification cs.LG updates on arXiv.org · 19d ago Deep Learning Approaches for Sleep Apnea Classification from Polysomnographic EEG Signals cs.LG updates on arXiv.org · 19d ago Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations cs.LG updates on arXiv.org · 19d ago Diffusion models recover accurate mixture weights despite score function insensitivity cs.LG updates on arXiv.org · 19d ago An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism cs.LG updates on arXiv.org · 19d ago Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching cs.LG updates on arXiv.org · 19d ago Recursive Harness Self-Improvement cs.LG updates on arXiv.org · 19d ago Design-Based Supervised Learning with Noisy Human Labels stat.ML updates on arXiv.org · 19d ago Retraining Seeks Stable Signals stat.ML updates on arXiv.org · 19d ago Which Hyperparameters Matter? A Game-Theoretic Framework for Interpretable Hyperparameter Sensitivity Analysis stat.ML updates on arXiv.org · 19d ago Deep and Probabilistic Models for Gene Regulatory Network Inference stat.ML updates on arXiv.org · 19d ago Cluster-Aware Matching via Laplacian Optimal Transport stat.ML updates on arXiv.org · 19d ago Proactive Inpatient Bed Requests for Emergency Department Admissions stat.ML updates on arXiv.org · 19d ago Prediction-Only Distillation in Linear and Logistic Regression stat.ML updates on arXiv.org · 19d ago Diffusion models recover accurate mixture weights despite score function insensitivity stat.ML updates on arXiv.org · 19d ago On the Role of Normalization in Binary Iterative Hard Thresholding for 1-bit Compressed Sensing stat.ML updates on arXiv.org · 19d ago Do Generative Models Keep Time? A Time-Aware Evaluation of Synthetic Sequential Tabular Data stat.ML updates on arXiv.org · 19d ago ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Language stat.ML updates on arXiv.org · 19d ago Aggregation of Statistical Evidence under Exchangeability stat.ML updates on arXiv.org · 19d ago Dimension-invariant uniform consistency of the empirical spatial distribution function and its associated spatial depth estimator stat.ML updates on arXiv.org · 19d ago An Efficient Likelihood Ratio Test for Online Changepoint Detection in the Presence of Autocorrelation stat.ML updates on arXiv.org · 19d ago Manifold Dimension Estimation via Local Graph Structure stat.ML updates on arXiv.org · 19d ago Improving Backward Conformal Prediction via Non-Conformity Score Transformation stat.ML updates on arXiv.org · 19d ago Conformal Graph Prediction with Z-Gromov-Wasserstein Distances stat.ML updates on arXiv.org · 19d ago Following the questions where they lead MIT News - Artificial intelligence · 21d ago Introducing Gemini 3.5 Flash Cyber Google DeepMind News · 21d ago Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods cs.LG updates on arXiv.org · 22d ago CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models cs.LG updates on arXiv.org · 22d ago Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence cs.LG updates on arXiv.org · 22d ago Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees cs.LG updates on arXiv.org · 22d ago QFireNet: A Quantum-Enhanced U-Net for Wildfire Segmentation from Sentinel-2 Imagery cs.LG updates on arXiv.org · 22d ago Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning cs.LG updates on arXiv.org · 22d ago How Much of a 10-K Matters? Aggregation-Dependent Value of Full-Text versus Risk-Factor Sentiment cs.LG updates on arXiv.org · 22d ago Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features cs.LG updates on arXiv.org · 22d ago RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences cs.LG updates on arXiv.org · 22d ago Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape cs.LG updates on arXiv.org · 22d ago A Temporal Machine Learning-Based Time-to-Event Model for Predicting ALS Progression and Healthcare Utilization cs.LG updates on arXiv.org · 22d ago TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories cs.LG updates on arXiv.org · 22d ago Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning cs.LG updates on arXiv.org · 22d ago Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games cs.LG updates on arXiv.org · 22d ago Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks cs.LG updates on arXiv.org · 22d ago LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks cs.LG updates on arXiv.org · 22d ago MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion cs.LG updates on arXiv.org · 22d ago Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist cs.LG updates on arXiv.org · 22d ago Lyapunov Guidance: A Unified Framework for Stabilizing Generative Flows cs.LG updates on arXiv.org · 22d ago NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis cs.LG updates on arXiv.org · 22d ago Generalized Neural Distributional Regression stat.ML updates on arXiv.org · 22d ago Operator-Informed Gaussian Processes for Complex Helmholtz Wavefields: From Synthetic Benchmarks to In Vivo Brain Elastography stat.ML updates on arXiv.org · 22d ago Spectral Concentration and Recovery in Sparse High-Dimensional Random Geometric Graphs stat.ML updates on arXiv.org · 22d ago Optimal Self-Distillation for Rectified Flow via Linear Probing stat.ML updates on arXiv.org · 22d ago cGAP: Generalized Association Plots with HOMALS-Guided Heatmaps for Visualization of High-Dimensional Categorical Data stat.ML updates on arXiv.org · 22d ago Subjective Risk Decomposition: A New View for Uncertainty Quantification stat.ML updates on arXiv.org · 22d ago PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter stat.ML updates on arXiv.org · 22d ago A Temporal Machine Learning-Based Time-to-Event Model for Predicting ALS Progression and Healthcare Utilization stat.ML updates on arXiv.org · 22d ago Parsimonious Mixtures of Skewed Bilinear Factor Analyzers stat.ML updates on arXiv.org · 22d ago NeuralChaos: Optimal Adapted Approximation of Square Integrable Predictable Processes stat.ML updates on arXiv.org · 22d ago Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion stat.ML updates on arXiv.org · 22d ago Precise sample covariance spectral norm error -- an RDT view stat.ML updates on arXiv.org · 22d ago Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers stat.ML updates on arXiv.org · 22d ago Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data stat.ML updates on arXiv.org · 22d ago Sharp Stability Threshold and Certification for Designing Stable Residual Architectures stat.ML updates on arXiv.org · 22d ago What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity stat.ML updates on arXiv.org · 22d ago GAttNHP: Group Attention Neural Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs stat.ML updates on arXiv.org · 22d ago Post Hoc Inference for Component Attribution in Multivariate Change-Point Detection stat.ML updates on arXiv.org · 22d ago Tamed Stochastic Gradient Hamiltonian Monte Carlo stat.ML updates on arXiv.org · 22d ago Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin stat.ML updates on arXiv.org · 22d ago Our approach to bioresilience Google DeepMind News · 23d ago Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks cs.LG updates on arXiv.org · 23d ago Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning cs.LG updates on arXiv.org · 23d ago Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges cs.LG updates on arXiv.org · 23d ago What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry cs.LG updates on arXiv.org · 23d ago Targeted Recovery of Weight-Space Mechanisms From Neural Networks cs.LG updates on arXiv.org · 23d ago Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems cs.LG updates on arXiv.org · 23d ago TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling cs.LG updates on arXiv.org · 23d ago Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing cs.LG updates on arXiv.org · 23d ago STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting cs.LG updates on arXiv.org · 23d ago A Hybrid Mamba for Audio-Visual Navigation cs.LG updates on arXiv.org · 23d ago CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion cs.LG updates on arXiv.org · 23d ago ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation cs.LG updates on arXiv.org · 23d ago HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtration cs.LG updates on arXiv.org · 23d ago SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy cs.LG updates on arXiv.org · 23d ago Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes cs.LG updates on arXiv.org · 23d ago EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting cs.LG updates on arXiv.org · 23d ago Reassessing Muon for Matrix Factorization cs.LG updates on arXiv.org · 23d ago Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners cs.LG updates on arXiv.org · 23d ago Tabular Foundation Models for Discrete Choice Estimation cs.LG updates on arXiv.org · 23d ago Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting cs.LG updates on arXiv.org · 23d ago Price of Fairness in Bandits: A Tight Minimax Characterization stat.ML updates on arXiv.org · 23d ago Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration stat.ML updates on arXiv.org · 23d ago Parallel gradient boosting for flexible estimation of conditional distributions stat.ML updates on arXiv.org · 23d ago Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling stat.ML updates on arXiv.org · 23d ago Wasserstein gradient flows for Coulomb discrepancies stat.ML updates on arXiv.org · 23d ago What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry stat.ML updates on arXiv.org · 23d ago Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems stat.ML updates on arXiv.org · 23d ago Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis stat.ML updates on arXiv.org · 23d ago Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs stat.ML updates on arXiv.org · 23d ago Cluster with Auctions for Vector Search stat.ML updates on arXiv.org · 23d ago DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention stat.ML updates on arXiv.org · 23d ago Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations stat.ML updates on arXiv.org · 23d ago Heavy-Tailed Flow Matching via Random Clocks stat.ML updates on arXiv.org · 23d ago Verifying formulas for interventional distributions stat.ML updates on arXiv.org · 23d ago Plausible Deniability Guarantees for Whistleblowers stat.ML updates on arXiv.org · 23d ago Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression stat.ML updates on arXiv.org · 23d ago Linear Independent Component Analysis via Optimal Transport stat.ML updates on arXiv.org · 23d ago Adaptive Conformal Inference through the Lens of Blackwell Approachability stat.ML updates on arXiv.org · 23d ago Leveraging Differentiable PDE Solvers for Semi-Neural Spatial Reconstruction From Sparse Measurements stat.ML updates on arXiv.org · 23d ago Convergence Rates for Distribution Matching with Sliced Optimal Transport stat.ML updates on arXiv.org · 23d ago A better way to turn 2D designs into 3D models for rapid prototyping MIT News - Artificial intelligence · 23d ago A better way to turn 2D designs into 3D models for rapid prototyping MIT News - Machine learning · 23d ago 3 Questions: Neural transparency and the future of AI design MIT News - Artificial intelligence · 23d ago 3 Questions: Neural transparency and the future of AI design MIT News - Machine learning · 23d ago Towards demystifying the creativity of diffusion models The latest research from Google · 23d ago OmniPMNet: Bridging discrete and gridded PM10 forecasts via omni-query neural processes cs.LG updates on arXiv.org · 24d ago Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels cs.LG updates on arXiv.org · 24d ago Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry cs.LG updates on arXiv.org · 24d ago Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding cs.LG updates on arXiv.org · 24d ago Mirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection cs.LG updates on arXiv.org · 24d ago Mathematics of Data Science cs.LG updates on arXiv.org · 24d ago CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA cs.LG updates on arXiv.org · 24d ago How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit cs.LG updates on arXiv.org · 24d ago BattVAE-GP: Generative Modeling of Long-Horizon Battery Degradation with Uncertainty Quantification cs.LG updates on arXiv.org · 24d ago Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite cs.LG updates on arXiv.org · 24d ago Scale-Aware Attention for Scarce Neural Data: An RG-Flow Transformer on Sleep-EDF EEG cs.LG updates on arXiv.org · 24d ago Scalable Optimal Transport Algorithm for Network Alignment cs.LG updates on arXiv.org · 24d ago When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary cs.LG updates on arXiv.org · 24d ago Graph-Constrained Policy Learning for Extreme Clinical Code Prediction cs.LG updates on arXiv.org · 24d ago Exact and Certified Data Shapley for Weighted k-Nearest-Neighbor Regression and Soft-Label Prediction cs.LG updates on arXiv.org · 24d ago Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle cs.LG updates on arXiv.org · 24d ago Evaluating Reliability in Machine Learning Models for Early Chronic Kidney Disease Prediction: A Systematic Review of Data Leakage and Predictor Stability cs.LG updates on arXiv.org · 24d ago LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving cs.LG updates on arXiv.org · 24d ago Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse cs.LG updates on arXiv.org · 24d ago Self-Evolving In-Context Learning for Direct Pilot-to-Beamformer Design in MU-MISO Systems cs.LG updates on arXiv.org · 24d ago Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection stat.ML updates on arXiv.org · 24d ago Learning the Graphical Nature of Symmetries stat.ML updates on arXiv.org · 24d ago Dynamic Online Processor-Native Inference for State Estimation stat.ML updates on arXiv.org · 24d ago Falsifying Causal Graphs With Outlier Events stat.ML updates on arXiv.org · 24d ago Thompson Sampling Is 2-Competitive for Mistakes stat.ML updates on arXiv.org · 24d ago Contrast-Free ICA and Causal Inference via Wasserstein Distances to the Gaussian stat.ML updates on arXiv.org · 24d ago ANGLE: Angular Neural Generative Learning via Engression stat.ML updates on arXiv.org · 24d ago Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo stat.ML updates on arXiv.org · 24d ago LatentFlow: A General Framework for Conditioning Stochastic Processes stat.ML updates on arXiv.org · 24d ago Ensemble Controlled-Flow Filtering for Implicit Data Assimilation stat.ML updates on arXiv.org · 24d ago Removable Defects: The Economics and Limits of Deliberate Deficiency stat.ML updates on arXiv.org · 24d ago Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs stat.ML updates on arXiv.org · 24d ago Causal Graphs, Markov Properties and Do-calculus for Stochastic Differential Equations stat.ML updates on arXiv.org · 24d ago Cluster-Weighted EDMD stat.ML updates on arXiv.org · 24d ago Forecasting Inflation with Microdata: An Adaptive Machine Learning Approach stat.ML updates on arXiv.org · 24d ago Statistical Properties and Power Analysis of Divergence Measures for Credit Risk Model Monitoring stat.ML updates on arXiv.org · 24d ago PolarBM: Complex-valued Boltzmann Machine for Modeling Audio Signals in Polar and Log-polar Coordinates stat.ML updates on arXiv.org · 24d ago Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise stat.ML updates on arXiv.org · 24d ago What Does Goodness Measure? A Likelihood-Ratio Account of Forward-Forward Learning stat.ML updates on arXiv.org · 24d ago MixCIT: A Kernel Based Local-Polynomial Debiased Test for Conditional Independence on Mixed-Type Data stat.ML updates on arXiv.org · 24d ago Helping AI models to meet the real world MIT News - Artificial intelligence · 24d ago Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering MIT News - Artificial intelligence · 24d ago Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering MIT News - Machine learning · 24d ago Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey cs.LG updates on arXiv.org · 25d ago Position: Every Ground Truth is a Human Construction, not an Objective Truth cs.LG updates on arXiv.org · 25d ago AuditWeave: A Tamper-Evident, Auditor-Navigable Evidence Layer for AI-Assisted and Data-Transformation Workflows cs.LG updates on arXiv.org · 25d ago Ablation, Statistical Inference, and Validation for KV-Cache Compression cs.LG updates on arXiv.org · 25d ago SciML in the Wild: A Diagnostic Study of When Structural Priors Help and When They Hurt cs.LG updates on arXiv.org · 25d ago MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference cs.LG updates on arXiv.org · 25d ago Prioritizing Search Space Regions in the Low Autocorrelation Binary Sequences Problem cs.LG updates on arXiv.org · 25d ago What Context Does a Coding Agent Actually Need to Act? cs.LG updates on arXiv.org · 25d ago Reference-Based Distillation Detection in LLMs cs.LG updates on arXiv.org · 25d ago Depth-Entropy Guided Sampling for Training-Free LLM Reasoning cs.LG updates on arXiv.org · 25d ago Low-Rank Attention Residuals cs.LG updates on arXiv.org · 25d ago FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift cs.LG updates on arXiv.org · 25d ago Mitigating Early Training Collapse in CTR Models cs.LG updates on arXiv.org · 25d ago Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs cs.LG updates on arXiv.org · 25d ago Quantum-Inspired Contextual Learning for Sparse-Ring Fraud Detection in Dynamic Transaction Graphs cs.LG updates on arXiv.org · 25d ago Manifold Constrained Tabular Deep Neural Networks cs.LG updates on arXiv.org · 25d ago EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs? cs.LG updates on arXiv.org · 25d ago ERP Data Provisioning Financial Control Testing cs.LG updates on arXiv.org · 25d ago Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls cs.LG updates on arXiv.org · 25d ago Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels cs.LG updates on arXiv.org · 25d ago Manifold Constrained Conformal Prediction for Spatial Events stat.ML updates on arXiv.org · 25d ago TSCoNet: A Two-Stage Copula CNN-LSTM for Uncertainty-Aware Spatio-Temporal Forecasting stat.ML updates on arXiv.org · 25d ago Integrating Background Knowledge for Scalable Causal Discovery stat.ML updates on arXiv.org · 25d ago Representation Learning for Semiparametric Causal Mediation Analysis under No Essential Heterogeneity stat.ML updates on arXiv.org · 25d ago Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering stat.ML updates on arXiv.org · 25d ago Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width stat.ML updates on arXiv.org · 25d ago Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization stat.ML updates on arXiv.org · 25d ago Edge Cluster Expansion with Radial Rotary Attention for Interatomic Potentials stat.ML updates on arXiv.org · 25d ago Long-Memory Reservoir Computing for Data-Scarce Dengue Forecasting stat.ML updates on arXiv.org · 25d ago Diversified Multinomial Logit Contextual Bandits stat.ML updates on arXiv.org · 25d ago Manifold Constrained Tabular Deep Neural Networks stat.ML updates on arXiv.org · 25d ago Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data stat.ML updates on arXiv.org · 25d ago Conservation Laws for Diffusion Models stat.ML updates on arXiv.org · 25d ago Energy-guided Recursive Model stat.ML updates on arXiv.org · 25d ago The Differential Neural Tangent Kernel and Its Positivity stat.ML updates on arXiv.org · 25d ago Learning from Local Walks on Dynamic Graphs with Bandit Feedback stat.ML updates on arXiv.org · 25d ago An Extreme Value Perspective on Learning Stress Laws stat.ML updates on arXiv.org · 25d ago GNet: A scalable and flexible Gaussian process network with nonparametric neurons stat.ML updates on arXiv.org · 25d ago Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures stat.ML updates on arXiv.org · 25d ago The Spectral Structure of Latent Treatment Effects stat.ML updates on arXiv.org · 25d ago How MIT students are helping to prevent cyberattacks MIT News - Artificial intelligence · 25d ago AI agents create virtual playgrounds to help robots get crucial training data MIT News - Artificial intelligence · 25d ago AI agents create virtual playgrounds to help robots get crucial training data MIT News - Machine learning · 25d ago Verifying Rust cryptography in SymCrypt, from standards to code Microsoft Research · 25d ago Empowering India’s next generation of innovators with ATL Saathi Google DeepMind News · 25d ago What building Shippy taught us about building agents Ai2 Blog · 26d ago A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions cs.LG updates on arXiv.org · 26d ago iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis cs.LG updates on arXiv.org · 26d ago Signed Symmetric Quantization for Few-Bit Integers cs.LG updates on arXiv.org · 26d ago Sticky Routing: Training MoE Models for Memory-Efficient Inference cs.LG updates on arXiv.org · 26d ago Reward Transport: Property Control in Flow Matching via Noise-Space Alignment cs.LG updates on arXiv.org · 26d ago Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement cs.LG updates on arXiv.org · 26d ago LieBN: Batch Normalization over Lie Groups cs.LG updates on arXiv.org · 26d ago HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning cs.LG updates on arXiv.org · 26d ago DaDaDa: A Dataset for Data Pricing in Data Marketplaces cs.LG updates on arXiv.org · 26d ago Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices cs.LG updates on arXiv.org · 26d ago Adaptive Bayes exactly tracks information over intrinsic time cs.LG updates on arXiv.org · 26d ago Prompt-Driven Exploration cs.LG updates on arXiv.org · 26d ago How are linear representations learned? Exact solutions to the dynamics of abstraction cs.LG updates on arXiv.org · 26d ago Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal cs.LG updates on arXiv.org · 26d ago Pattern-Aware Graph Neural Networks for Handling Missing Data cs.LG updates on arXiv.org · 26d ago A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks cs.LG updates on arXiv.org · 26d ago SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions cs.LG updates on arXiv.org · 26d ago BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving cs.LG updates on arXiv.org · 26d ago TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning cs.LG updates on arXiv.org · 26d ago Training, Reading, and Editing Legible Transformers cs.LG updates on arXiv.org · 26d ago EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins stat.ML updates on arXiv.org · 26d ago Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics stat.ML updates on arXiv.org · 26d ago Spectrally Deconfounded Gradient Boosting stat.ML updates on arXiv.org · 26d ago Characterization of the basin of convexity for multi-snapshot spike deconvolution via variable projection stat.ML updates on arXiv.org · 26d ago Deep Gaussian Processes on Directed Acyclic Graphs stat.ML updates on arXiv.org · 26d ago Adaptive Bayes exactly tracks information over intrinsic time stat.ML updates on arXiv.org · 26d ago A Statistical Test for the Benefits of Personalizing Interventions stat.ML updates on arXiv.org · 26d ago Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity stat.ML updates on arXiv.org · 26d ago Stochastic Linear Bandits with Partially Observed Actions stat.ML updates on arXiv.org · 26d ago Optimal Top-$k$ Identification from Pairwise Comparisons stat.ML updates on arXiv.org · 26d ago Achieving Almost Exact Recovery in Almost Quadratic Time: Rank-Based Graph Matching via Local Tree Correlation Tests stat.ML updates on arXiv.org · 26d ago Solving Stochastic Fixed-Point Equations with High Probability stat.ML updates on arXiv.org · 26d ago Similarity search generalisation in contrastive learning with InfoNCE loss stat.ML updates on arXiv.org · 26d ago comprisk: A scikit-learn-compatible Python toolkit for competing-risks survival analysis stat.ML updates on arXiv.org · 26d ago Near-optimal node-private community estimation in polynomial-time stat.ML updates on arXiv.org · 26d ago Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions stat.ML updates on arXiv.org · 26d ago Neural Collapse Is Forbidden: Information Floors in Language Models stat.ML updates on arXiv.org · 26d ago Terminal Dimension Reduction for Time Series with Applications stat.ML updates on arXiv.org · 26d ago Statistically Undetectable Backdoors in Deep Neural Networks stat.ML updates on arXiv.org · 26d ago High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations stat.ML updates on arXiv.org · 26d ago New method aims to keep kids safe from illegal AI-generated content MIT News - Artificial intelligence · 26d ago New method aims to keep kids safe from illegal AI-generated content MIT News - Machine learning · 26d ago Amazon and University of Michigan give robots a sense of touch Amazon Science homepage · 28d ago Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution cs.LG updates on arXiv.org · 29d ago Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification cs.LG updates on arXiv.org · 29d ago LLT: Local Linear Transformer for PDE Operator Learning cs.LG updates on arXiv.org · 29d ago ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning cs.LG updates on arXiv.org · 29d ago Omni-Sleep: A Sleep Foundation Model via Hierarchical Contrastive Learning of CNS--ANS Dynamic cs.LG updates on arXiv.org · 29d ago Uncertainty-gated selection for block-sparse attention cs.LG updates on arXiv.org · 29d ago SHIFT: Survival Prediction from Incomplete and Heterogeneous Genomic Data cs.LG updates on arXiv.org · 29d ago Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE cs.LG updates on arXiv.org · 29d ago Architecture Generalization with MetaNCA cs.LG updates on arXiv.org · 29d ago LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks cs.LG updates on arXiv.org · 29d ago Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation cs.LG updates on arXiv.org · 29d ago A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents cs.LG updates on arXiv.org · 29d ago Image classification via a quantum-inspired strategy involving a mixture of experts cs.LG updates on arXiv.org · 29d ago The Importance of Encoder Choice:A Tabular-Image Study cs.LG updates on arXiv.org · 29d ago Scalable and Trustworthy Earth Observation Foundation Models cs.LG updates on arXiv.org · 29d ago Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives cs.LG updates on arXiv.org · 29d ago Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models cs.LG updates on arXiv.org · 29d ago Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms cs.LG updates on arXiv.org · 29d ago Graph-Regularized Deep Learning for EEG-Based Emotion Recognition with Psychologically-Grounded Label Structure cs.LG updates on arXiv.org · 29d ago A law of robustness for two-layer neural networks with arbitrary weights cs.LG updates on arXiv.org · 29d ago The Regularization Parameter: Sparse Precision Matrix Estimation stat.ML updates on arXiv.org · 29d ago Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation stat.ML updates on arXiv.org · 29d ago Expressivity and Statistical Trade-offs in Diffusion Policy Learning stat.ML updates on arXiv.org · 29d ago Bayesian Experimental Design via Score Matching stat.ML updates on arXiv.org · 29d ago Prediction-Powered Active Testing stat.ML updates on arXiv.org · 29d ago Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning stat.ML updates on arXiv.org · 29d ago High-Dimensional Procrustes Matching via Tree Counts stat.ML updates on arXiv.org · 29d ago Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling stat.ML updates on arXiv.org · 29d ago Mathematical methods of reinforcement learning stat.ML updates on arXiv.org · 29d ago LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks stat.ML updates on arXiv.org · 29d ago A law of robustness for two-layer neural networks with arbitrary weights stat.ML updates on arXiv.org · 29d ago Mixtures of spatial factor analyzers for tensor-variate data stat.ML updates on arXiv.org · 29d ago Reinforcing the Generation Order of Multimodal Masked Diffusion Models stat.ML updates on arXiv.org · 29d ago Joint estimation of high-dimensional spiked covariance matrices via a partially shared subspace stat.ML updates on arXiv.org · 29d ago Selecting Interpretable Circular Coordinates from Data stat.ML updates on arXiv.org · 29d ago Structure Learning on Clustered Data stat.ML updates on arXiv.org · 29d ago An interpretable Good--Turing restart criterion for k-means++ stat.ML updates on arXiv.org · 29d ago A scalable version of MADD for big-data classification stat.ML updates on arXiv.org · 29d ago AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate stat.ML updates on arXiv.org · 29d ago Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks stat.ML updates on arXiv.org · 29d ago Aurora 1.5: Extending open foundation models for weather and Earth-system applications Microsoft Research · 29d ago Tiny robot boats build floating structures MIT News - Artificial intelligence · 29d ago Tiny robot boats build floating structures MIT News - Machine learning · 29d ago Capturing token IDs during agentic interactions for better reinforcement learning Amazon Science homepage · 29d ago SensorFM: Towards a general intelligence and interface for wearable health data The latest research from Google · 30d ago TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation cs.LG updates on arXiv.org · 30d ago A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It cs.LG updates on arXiv.org · 30d ago NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts cs.LG updates on arXiv.org · 30d ago D2PO: Optimizing Diffusion Samplers via Dynamic Preference cs.LG updates on arXiv.org · 30d ago Deep Reinforcement Learning for Reliability Based Bi-Objective Portfolio Optimization cs.LG updates on arXiv.org · 30d ago STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting cs.LG updates on arXiv.org · 30d ago WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning cs.LG updates on arXiv.org · 30d ago Inertia-1: An Open Exploration of Wearable Motion Foundation Models cs.LG updates on arXiv.org · 30d ago Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention cs.LG updates on arXiv.org · 30d ago LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting cs.LG updates on arXiv.org · 30d ago Open-Ended Scenario Reasoning for Specialist Model Adaptation cs.LG updates on arXiv.org · 30d ago Reward Valuation in Vision Language Models: Causal Mechanisms Underlying Anhedonia cs.LG updates on arXiv.org · 30d ago Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking cs.LG updates on arXiv.org · 30d ago STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning cs.LG updates on arXiv.org · 30d ago When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models cs.LG updates on arXiv.org · 30d ago Does Demand Response Increase Vulnerability to Cyber Attacks by Adversarial Data Modifications? cs.LG updates on arXiv.org · 30d ago When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws cs.LG updates on arXiv.org · 30d ago Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers cs.LG updates on arXiv.org · 30d ago UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks cs.LG updates on arXiv.org · 30d ago At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics cs.LG updates on arXiv.org · 30d ago Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set stat.ML updates on arXiv.org · 30d ago Fast determinantal sampling on general spaces and diffusion geometry stat.ML updates on arXiv.org · 30d ago Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds stat.ML updates on arXiv.org · 30d ago Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling stat.ML updates on arXiv.org · 30d ago Finding a stationary point of a stochastic convex problem stat.ML updates on arXiv.org · 30d ago Tensorized algorithms and scalable filtering methods for hidden Markov and factorial hidden Markov models stat.ML updates on arXiv.org · 30d ago DiPhon: Diffusion on Graphons for Scalable Graph Generation stat.ML updates on arXiv.org · 30d ago Statistical inverse learning and $\ell^1$-regularization stat.ML updates on arXiv.org · 30d ago A Unified Detection Framework for AI-Related Content and Artifacts stat.ML updates on arXiv.org · 30d ago A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It stat.ML updates on arXiv.org · 30d ago From Jumps to Signatures: a Generative Method for Temporal Point Processes stat.ML updates on arXiv.org · 30d ago Best-Arm Identification with Generative Proxy stat.ML updates on arXiv.org · 30d ago Transfer Learning for Linear Discriminant Analysis with a Shared Classification Signal stat.ML updates on arXiv.org · 30d ago Local large deviations for linear-region growth in random piecewise-linear networks stat.ML updates on arXiv.org · 30d ago Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces stat.ML updates on arXiv.org · 30d ago The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought stat.ML updates on arXiv.org · 30d ago Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization stat.ML updates on arXiv.org · 30d ago Avoiding unsafe sets when training with Langevin Dynamics stat.ML updates on arXiv.org · 30d ago Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer stat.ML updates on arXiv.org · 30d ago Optimal Conformal Prediction under Epistemic Uncertainty stat.ML updates on arXiv.org · 30d ago MIT-designed educational factory embraces modern manufacturing MIT News - Machine learning · 30d ago Flint: A visualization language for the AI era Microsoft Research · 30d ago MolmoAct 2 shows what open models can unlock for robotics Ai2 Blog · 31d ago Statistically Meaningful Geometry and Gauge Symmetry Breaking: A Geometric Foundation for Scientific Discovery and Intelligence Emergence cs.LG updates on arXiv.org · 31d ago Design-CP: Context Parallelism for Design of Protein Nanoparticles cs.LG updates on arXiv.org · 31d ago Geometry-Aware Infrastructure-Anchored Denoiser for UWB Sensing and Work-Zone Reconstruction cs.LG updates on arXiv.org · 31d ago The Granularity Paradox: How Temporal Disaggregation Inflates In-Sample Fit and Compounds Out-of-Sample Error cs.LG updates on arXiv.org · 31d ago Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates cs.LG updates on arXiv.org · 31d ago Empirical Minimal-Realisation Compression of Deep Neural Networks via Controllability-Observability Tests cs.LG updates on arXiv.org · 31d ago Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning cs.LG updates on arXiv.org · 31d ago AdaStop: Cost-Aware Early Stopping for DNN Test Selection cs.LG updates on arXiv.org · 31d ago Learnable Weighting of Intra-Attribute Distances for Categorical Data Clustering with Nominal and Ordinal Attributes cs.LG updates on arXiv.org · 31d ago Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy cs.LG updates on arXiv.org · 31d ago Parameter-Free Encoders Remain Viable for RDB Foundation Models cs.LG updates on arXiv.org · 31d ago InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs cs.LG updates on arXiv.org · 31d ago PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates cs.LG updates on arXiv.org · 31d ago $\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse cs.LG updates on arXiv.org · 31d ago Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation cs.LG updates on arXiv.org · 31d ago Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids cs.LG updates on arXiv.org · 31d ago EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation cs.LG updates on arXiv.org · 31d ago SafeImpute: Reliable Clinical Data Imputation via Conformal Selection cs.LG updates on arXiv.org · 31d ago A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models cs.LG updates on arXiv.org · 31d ago Safe Bayesian Optimization with Counterfactual Policies cs.LG updates on arXiv.org · 31d ago Higher-Order Certified Robustness for Regression stat.ML updates on arXiv.org · 31d ago Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity stat.ML updates on arXiv.org · 31d ago To Retain or to Adapt? Generalizing Continual Learning stat.ML updates on arXiv.org · 31d ago Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking stat.ML updates on arXiv.org · 31d ago Width-Robust Learnability in Mean-Field Bayesian Neural Networks stat.ML updates on arXiv.org · 31d ago Boosting with List-Decodable Codes stat.ML updates on arXiv.org · 31d ago On the convergence of graph Laplacians with a symmetric divergence stat.ML updates on arXiv.org · 31d ago Separation Capacity of Scattering Networks on Low-Dimensional Datasets stat.ML updates on arXiv.org · 31d ago A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems stat.ML updates on arXiv.org · 31d ago A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel stat.ML updates on arXiv.org · 31d ago Exact computation of posterior distribution of mixture weights in hierarchical Bayesian models stat.ML updates on arXiv.org · 31d ago No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training stat.ML updates on arXiv.org · 31d ago Stochastic generator of trajectories from record data: application to the fluctuations of a glacier's frontal position from a sample of moraines stat.ML updates on arXiv.org · 31d ago Closed-form fractional radial links for elliptical Mahalanobis discriminant analysis stat.ML updates on arXiv.org · 31d ago Quantitative Gaussian-Process limits of Tensor Programs stat.ML updates on arXiv.org · 31d ago A unified perspective of Gaussian process approximation for differential equations stat.ML updates on arXiv.org · 31d ago Approximate Risk Minimization Over Shrinking-Thresholding Rules in Normal Mean Estimation stat.ML updates on arXiv.org · 31d ago Factor-Augmented Machine Learning Panel Regressions stat.ML updates on arXiv.org · 31d ago Feature Learning for the High Dimensional Stationary Sch\"odinger Equation with Deep Ritz Method stat.ML updates on arXiv.org · 31d ago EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning stat.ML updates on arXiv.org · 31d ago How novice coders can develop AI programs for military applications MIT News - Artificial intelligence · 31d ago The power of collaboration: How we can reduce traffic congestion The latest research from Google · 31d ago Jesse Thaler named director of the Laboratory for Nuclear Science MIT News - Artificial intelligence · 31d ago Intelligence is Free, Now What? <br> Data Systems for, of, and by Agents The Berkeley Artificial Intelligence Research Blog · 32d ago Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits cs.LG updates on arXiv.org · 32d ago Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence cs.LG updates on arXiv.org · 32d ago QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting cs.LG updates on arXiv.org · 32d ago GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech cs.LG updates on arXiv.org · 32d ago Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data cs.LG updates on arXiv.org · 32d ago Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting cs.LG updates on arXiv.org · 32d ago A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction cs.LG updates on arXiv.org · 32d ago LiNO: Lifting based multiresolution neural operator cs.LG updates on arXiv.org · 32d ago Weighted Conformal Prediction for Lab-to-Track Thermal Transfer in EV Motorsport Powertrains cs.LG updates on arXiv.org · 32d ago Out-of-Distribution Generalization of Risk Aversion in Language Models cs.LG updates on arXiv.org · 32d ago Safe Inference-Time Alignment via Lagrangian Reward Augmentation cs.LG updates on arXiv.org · 32d ago Induction Heads Interpolate N-Grams cs.LG updates on arXiv.org · 32d ago Training Hybrid Block Diffusion Language Models with Partial Bidirectionality cs.LG updates on arXiv.org · 32d ago Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction cs.LG updates on arXiv.org · 32d ago On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization cs.LG updates on arXiv.org · 32d ago Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data cs.LG updates on arXiv.org · 32d ago Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading cs.LG updates on arXiv.org · 32d ago Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models cs.LG updates on arXiv.org · 32d ago Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs cs.LG updates on arXiv.org · 32d ago Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions cs.LG updates on arXiv.org · 32d ago CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation stat.ML updates on arXiv.org · 32d ago Benign Overfitting Does Not Occur in Diffusion Models stat.ML updates on arXiv.org · 32d ago Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms stat.ML updates on arXiv.org · 32d ago Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions stat.ML updates on arXiv.org · 32d ago A Hierarchy of Policy Learning Problems stat.ML updates on arXiv.org · 32d ago Missing Data Imputation under Manifold Hypothesis stat.ML updates on arXiv.org · 32d ago Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch stat.ML updates on arXiv.org · 32d ago Robust Bayes-Assisted Conformal Prediction stat.ML updates on arXiv.org · 32d ago Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis stat.ML updates on arXiv.org · 32d ago Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models stat.ML updates on arXiv.org · 32d ago On Pairwise Quantile Regression -- Statistical Guarantees and Applications stat.ML updates on arXiv.org · 32d ago Tightening the Score Matching Gap for Diffusion Models stat.ML updates on arXiv.org · 32d ago Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data stat.ML updates on arXiv.org · 32d ago Integrating Neural Encoders in Bayesian Generalized Linear Mixed Models for Multimodal Data stat.ML updates on arXiv.org · 32d ago Decomposition for Bayesian Networks: Local and Parallel Inference stat.ML updates on arXiv.org · 32d ago Wasserstein Residuals: Learning Gradient Flows from Population Dynamics stat.ML updates on arXiv.org · 32d ago Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models stat.ML updates on arXiv.org · 32d ago Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling stat.ML updates on arXiv.org · 32d ago Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation stat.ML updates on arXiv.org · 32d ago Geometric Causal Models stat.ML updates on arXiv.org · 32d ago How Open Models Are Driving AI Research NVIDIA Research Archives | NVIDIA Blog · 32d ago Google DeepMind and A24 announce first-of-its-kind research partnership Google DeepMind News · 35d ago Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability cs.LG updates on arXiv.org · 36d ago I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals cs.LG updates on arXiv.org · 36d ago Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery cs.LG updates on arXiv.org · 36d ago Domain Knowledge Based Temporal-Spatial Graph Convolution Network for ECG Recognition cs.LG updates on arXiv.org · 36d ago Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions cs.LG updates on arXiv.org · 36d ago IonSense-QKG: A Quantum-Readiness Metadata Framework for Lithium-Ion Battery Dataset Discovery cs.LG updates on arXiv.org · 36d ago A Novel Machine Learning Approach for Central Nervous System Tumor Classification from DNA Methylation cs.LG updates on arXiv.org · 36d ago From Approximation to Emergence: A Theory of Deep Learning cs.LG updates on arXiv.org · 36d ago Black-Box Inference of LLM Architectural Properties with Restrictive API Access cs.LG updates on arXiv.org · 36d ago Multi-modal Rail Crossing Safety Analysis cs.LG updates on arXiv.org · 36d ago How Should Transformers Encode Numeric Values in Electronic Health Records? cs.LG updates on arXiv.org · 36d ago NeuroBridge: Bridging Multi-Task MRI Knowledge for Neurodegenerative Disease Diagnosis cs.LG updates on arXiv.org · 36d ago Spin-Weighted Spherical Harmonics Enable Complete and Scalable $\mathrm{E}(3)$-Equivariant Networks cs.LG updates on arXiv.org · 36d ago The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning cs.LG updates on arXiv.org · 36d ago Conditional Inference Trees and Forests for Feature Selection cs.LG updates on arXiv.org · 36d ago On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain cs.LG updates on arXiv.org · 36d ago Geometry-Aware R-Structured Kolmogorov-Arnold Networks cs.LG updates on arXiv.org · 36d ago Token Geometry cs.LG updates on arXiv.org · 36d ago Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning cs.LG updates on arXiv.org · 36d ago How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size cs.LG updates on arXiv.org · 36d ago eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions stat.ML updates on arXiv.org · 36d ago Full Bayesian Reinforcement Learning via LF-IBIS stat.ML updates on arXiv.org · 36d ago Statistical Properties of $k$-means Clustering for Data Missing Completely at Random stat.ML updates on arXiv.org · 36d ago Autorelevance function and other feature relevance measures for univariate time series stat.ML updates on arXiv.org · 36d ago Born Discrete, Made Smooth: Variational Formulation of Shallow Neural Networks stat.ML updates on arXiv.org · 36d ago Prediction Sets for Counterfactual Decisions: Coverage, Optimality, and Conformal Prediction stat.ML updates on arXiv.org · 36d ago An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility stat.ML updates on arXiv.org · 36d ago The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry stat.ML updates on arXiv.org · 36d ago From Approximation to Emergence: A Theory of Deep Learning stat.ML updates on arXiv.org · 36d ago Conditional Inference Trees and Forests for Feature Selection stat.ML updates on arXiv.org · 36d ago How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size stat.ML updates on arXiv.org · 36d ago Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness stat.ML updates on arXiv.org · 36d ago Learning Effective Soliton Dynamics from Scattering Data stat.ML updates on arXiv.org · 36d ago Identifiability Limits of Physics-Informed Inference for Spatial Stochastic Dynamics from Static Snapshots stat.ML updates on arXiv.org · 36d ago Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning stat.ML updates on arXiv.org · 36d ago Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Model stat.ML updates on arXiv.org · 36d ago Moment-Based Selection of Multiresponse Linear Mixed-Effects Models stat.ML updates on arXiv.org · 36d ago Sequential Structure-Sensitive Residual Diagnostics for PDE Inverse Problems stat.ML updates on arXiv.org · 36d ago Conformal Bayes for Two-Sided Censored Gaussian Regression under Label Shift stat.ML updates on arXiv.org · 36d ago Aggregation with Exponential Weights is Optimal in Expectation stat.ML updates on arXiv.org · 36d ago Modular LLMs at scale: how FlexOlmo is helping to pool national expertise without pooling sensitive data Ai2 Blog · 37d ago Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol cs.LG updates on arXiv.org · 37d ago SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling cs.LG updates on arXiv.org · 37d ago SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification cs.LG updates on arXiv.org · 37d ago A Filtered Mixture-of-Generators for Fully Synthetic Survival Training cs.LG updates on arXiv.org · 37d ago GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity cs.LG updates on arXiv.org · 37d ago EVOTS: Evolutionary Transformer Search for Time Series Forecasting cs.LG updates on arXiv.org · 37d ago FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts cs.LG updates on arXiv.org · 37d ago Verifiable Rewards for Calibrated Probabilistic Forecasting cs.LG updates on arXiv.org · 37d ago Scaling Up Thermodynamic AI Models cs.LG updates on arXiv.org · 37d ago TallyTrain: Communication-Efficient Federated Distillation cs.LG updates on arXiv.org · 37d ago Play Like Champions: Counterfactual Feedback Generation in Latent Space cs.LG updates on arXiv.org · 37d ago TRIE: An Evaluation Framework for Stochastic PDE Surrogates cs.LG updates on arXiv.org · 37d ago StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting cs.LG updates on arXiv.org · 37d ago Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts cs.LG updates on arXiv.org · 37d ago Distributionally Robust Linear Regression With Block Lewis Weights cs.LG updates on arXiv.org · 37d ago Learning dynamical systems from noisy data with Weak-form Kernel Ridge Regression cs.LG updates on arXiv.org · 37d ago Validating Causal Abstraction Metrics on Simulated Complex Systems cs.LG updates on arXiv.org · 37d ago Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning cs.LG updates on arXiv.org · 37d ago Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds cs.LG updates on arXiv.org · 37d ago Understanding Guest Preferences and Optimizing Two-sided Marketplaces: Airbnb as an Example cs.LG updates on arXiv.org · 37d ago From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators stat.ML updates on arXiv.org · 37d ago Neural Network-Based Estimation of Time-Dependent Parameters in AR(p) Processes stat.ML updates on arXiv.org · 37d ago Hierarchical Variational Kalman Filtering stat.ML updates on arXiv.org · 37d ago Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity stat.ML updates on arXiv.org · 37d ago Function-Counting Theory for Low-Dimensional Data Structures stat.ML updates on arXiv.org · 37d ago Characterizing and Identifying Separable Graphical Models stat.ML updates on arXiv.org · 37d ago Measuring Racial Disparities in Rent Growth Under Algorithmic Landlord Concentration in U.S. Metros stat.ML updates on arXiv.org · 37d ago Uniform-in-time Propagation-of-Chaos for Stein Variational Gradient Descent stat.ML updates on arXiv.org · 37d ago GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity stat.ML updates on arXiv.org · 37d ago Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent stat.ML updates on arXiv.org · 37d ago Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics stat.ML updates on arXiv.org · 37d ago Distributionally Robust Linear Regression With Block Lewis Weights stat.ML updates on arXiv.org · 37d ago Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning stat.ML updates on arXiv.org · 37d ago Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization stat.ML updates on arXiv.org · 37d ago Prototype Language Models stat.ML updates on arXiv.org · 37d ago From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research stat.ML updates on arXiv.org · 37d ago Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization stat.ML updates on arXiv.org · 37d ago Approximate full-conformal multi-task regression with reproducing kernels stat.ML updates on arXiv.org · 37d ago Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry stat.ML updates on arXiv.org · 37d ago Decision-Aware Training for Sample-Based Generative Models stat.ML updates on arXiv.org · 37d ago How Amazon tracks carbon intensity across its operations Amazon Science homepage · 37d ago 2026 BAIR Graduate Showcase The Berkeley Artificial Intelligence Research Blog · 38d ago Joint discovery of governing partial differential equations from multi-source datasets by competitive optimization cs.LG updates on arXiv.org · 38d ago Accelerometry-Derived Digital Biomarkers for Cardiometabolic Risk: A Population-Representative Tabular Benchmark with Uncertainty Quantification cs.LG updates on arXiv.org · 38d ago From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators cs.LG updates on arXiv.org · 38d ago Why Do Few-Step Text Latents Fail When Image Latents Work? Non-Commitment at Sharp Categorical Readouts cs.LG updates on arXiv.org · 38d ago Hierarchical Global Attention (HGA) cs.LG updates on arXiv.org · 38d ago ReactionAtlas: Ab origine exploration of chemical reaction networks with machine learning cs.LG updates on arXiv.org · 38d ago Revocable Learned State via Process Sidecars cs.LG updates on arXiv.org · 38d ago Predictable GRPO: A Closed-Form Model of Training Dynamics cs.LG updates on arXiv.org · 38d ago Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization cs.LG updates on arXiv.org · 38d ago Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias cs.LG updates on arXiv.org · 38d ago Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization cs.LG updates on arXiv.org · 38d ago A Stationary-Distribution Theory for Triplet-Based Plateau Search in Random Forest Ensemble-Size Selection cs.LG updates on arXiv.org · 38d ago A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels cs.LG updates on arXiv.org · 38d ago Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback cs.LG updates on arXiv.org · 38d ago Personalizing Marketplace Policies with Competing Objectives and Constrained Experiments: Evidence from a Job Marketplace cs.LG updates on arXiv.org · 38d ago Quality-Aware Modulation for Diffusion Transformers cs.LG updates on arXiv.org · 38d ago Physics-informed Conditional Normalizing Flows for Angles-only Cislunar Orbit Determination cs.LG updates on arXiv.org · 38d ago Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again cs.LG updates on arXiv.org · 38d ago Estimating Supply Incrementality in Two-sided Marketplaces: A Causal Machine Learning Approach cs.LG updates on arXiv.org · 38d ago Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction cs.LG updates on arXiv.org · 38d ago Separation Capacity of Scattering Networks stat.ML updates on arXiv.org · 38d ago Dynamic Prediction of Alternating Recurrent Events via Neural Network stat.ML updates on arXiv.org · 38d ago SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates stat.ML updates on arXiv.org · 38d ago Dynamic Gaussian Processes and the Vanilla-SPDE Exchange stat.ML updates on arXiv.org · 38d ago MNAR-$k$-means: A $k$-means Clustering for Data Missing Not at Random with Magnitude-Decaying Probability stat.ML updates on arXiv.org · 38d ago Accelerating Conformal Prediction via Approximate Leave-One-Out stat.ML updates on arXiv.org · 38d ago MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis stat.ML updates on arXiv.org · 38d ago Horseshoe Priors for Spatial Small Area Estimation: Regular Variation, Tail Robustness, and Deep Learning stat.ML updates on arXiv.org · 38d ago Accelerometry-Derived Digital Biomarkers for Cardiometabolic Risk: A Population-Representative Tabular Benchmark with Uncertainty Quantification stat.ML updates on arXiv.org · 38d ago Predictable GRPO: A Closed-Form Model of Training Dynamics stat.ML updates on arXiv.org · 38d ago Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Product of Random Matrices stat.ML updates on arXiv.org · 38d ago A Stationary-Distribution Theory for Triplet-Based Plateau Search in Random Forest Ensemble-Size Selection stat.ML updates on arXiv.org · 38d ago Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback stat.ML updates on arXiv.org · 38d ago Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization stat.ML updates on arXiv.org · 38d ago Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again stat.ML updates on arXiv.org · 38d ago Can Tabular In-Context Learners Generalize to Biomolecular Property Prediction? stat.ML updates on arXiv.org · 38d ago Learning Gaussian Graphical Models from a Glauber Trajectory Without Mixing stat.ML updates on arXiv.org · 38d ago Sequential sparse Gaussian process quantile regression stat.ML updates on arXiv.org · 38d ago Contextual Slate GLM Bandits with Limited Adaptivity stat.ML updates on arXiv.org · 38d ago On the Convergence of Self-Improving Online LLM Alignment stat.ML updates on arXiv.org · 38d ago Expanding our Heat Resilience data to 50+ global cities The latest research from Google · 38d ago SkillOpt: Agent skills as trainable parameters Microsoft Research · 38d ago Start building with Nano Banana 2 Lite and Gemini Omni Flash Google DeepMind News · 38d ago Q&A: What is agentic AI today, and what do we want it to be? MIT News - Machine learning · 38d ago Introducing TabFM: A zero-shot foundation model for tabular data The latest research from Google · 39d ago Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models cs.LG updates on arXiv.org · 39d ago On the Necessity of a Liquid Substrate for Mesh Intelligence cs.LG updates on arXiv.org · 39d ago Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy cs.LG updates on arXiv.org · 39d ago Learning to Distributedly Estimate under Partially Known Dynamics: A Covariance-Agnostic Neural Kalman Consensus Filter cs.LG updates on arXiv.org · 39d ago S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights cs.LG updates on arXiv.org · 39d ago scKDGM: KAN-guided Dynamic Graph Masked Learning for Single-Cell RNA-seq Clustering cs.LG updates on arXiv.org · 39d ago Counterfactual Residual Data Augmentation for Regression cs.LG updates on arXiv.org · 39d ago Singular Learning and Occam's Razor in Deep Monomial Networks cs.LG updates on arXiv.org · 39d ago An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations cs.LG updates on arXiv.org · 39d ago Modelling Emotional Memory in Children with Tensor Networks cs.LG updates on arXiv.org · 39d ago A Trainable-by-Parts Operator Learning Framework: Bridging DeepONet and Karhunen-Loeve Expansions for Large-Scale Applications cs.LG updates on arXiv.org · 39d ago A Gravitational Interpretation of Fine-Tuning Reversion cs.LG updates on arXiv.org · 39d ago NIVA: A Multimodal Foundation Model for Actionable Earth System Intelligence cs.LG updates on arXiv.org · 39d ago Improving Coherence in Hierarchical Time Series Forecasting using Structured Temporal Fusion cs.LG updates on arXiv.org · 39d ago Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings cs.LG updates on arXiv.org · 39d ago Replica Symmetry Breaking and Algorithmic Thresholds in Empirical Risk Minimization under Multi-Index Model cs.LG updates on arXiv.org · 39d ago What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs cs.LG updates on arXiv.org · 39d ago Randomized Exploration for Linear Bandits via Absolute Perturbations cs.LG updates on arXiv.org · 39d ago Improving Patient Subtyping on Longitudinal Data using Representations from Mamba-based Architecture cs.LG updates on arXiv.org · 39d ago When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling cs.LG updates on arXiv.org · 39d ago Spectral Perturbation of the Empirical Fisher Information Matrix under Weight Quantization stat.ML updates on arXiv.org · 39d ago Adaptive Iterative Hard Thresholding for Online High-dimensional Quantile Regression stat.ML updates on arXiv.org · 39d ago Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms stat.ML updates on arXiv.org · 39d ago Perspectives on Latent Factor Indeterminacy and its Implications for Data Representation stat.ML updates on arXiv.org · 39d ago A Bayesian latent Gaussian process framework for aerodynamic uncertainty quantification stat.ML updates on arXiv.org · 39d ago Connectivity Estimation using Stochastic Graph Heat Modelling stat.ML updates on arXiv.org · 39d ago Generalization Analysis of Transformers in Distribution Regression stat.ML updates on arXiv.org · 39d ago Gradient boosting with vector-valued leafs stat.ML updates on arXiv.org · 39d ago Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery stat.ML updates on arXiv.org · 39d ago Bidirectional Autoregressive Latent Diffusion for Forward and Inverse Magnetohydrodynamics stat.ML updates on arXiv.org · 39d ago Adjusted Wasserstein distances for bridging empirical and true distributions with applications to MDS stat.ML updates on arXiv.org · 39d ago Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{\"o}dinger bridge stat.ML updates on arXiv.org · 39d ago Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions stat.ML updates on arXiv.org · 39d ago Extrapolating from Regularised Solutions for Solving Ill-Conditioned Linear Systems in Machine Learning stat.ML updates on arXiv.org · 39d ago A Stochastic--Geometric Theory of Scaling Laws in Grokking stat.ML updates on arXiv.org · 39d ago SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model stat.ML updates on arXiv.org · 39d ago Non-parametric recovery of causal diffusion mechanisms from steady-state observations stat.ML updates on arXiv.org · 39d ago Factorizable Normalizing Flows for parameter-dependent density morphing stat.ML updates on arXiv.org · 39d ago Doubly Robust Adaptive Conformal Inference for Causal Effects Under Temporal Dependence stat.ML updates on arXiv.org · 39d ago Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms stat.ML updates on arXiv.org · 39d ago Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity Microsoft Research · 39d ago Inaugural Music Technology Research Showcase celebrates work of new graduate program’s initial students MIT News - Machine learning · 39d ago 3 Questions: Beyond data-driven aesthetics MIT News - Machine learning · 39d ago OverFlowLight: Real-Time Gridlock Prevention and Traffic Signal Optimization for Urban Intersections cs.LG updates on arXiv.org · 40d ago RANSAC Scoring Done Right cs.LG updates on arXiv.org · 40d ago Unified Zero-Shot Time Series Forecasting: A Darts Foundation cs.LG updates on arXiv.org · 40d ago PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding cs.LG updates on arXiv.org · 40d ago Learning in Markovian bandits with non-observable states and constrained decision epochs cs.LG updates on arXiv.org · 40d ago Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing cs.LG updates on arXiv.org · 40d ago Operator Learning for Cubic Nonlinear Schr\"odinger Equation on Periodic Domains cs.LG updates on arXiv.org · 40d ago The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching cs.LG updates on arXiv.org · 40d ago Boundary condition fidelity for bottom-hole pressure and CO2 plume prediction in geological carbon storage cs.LG updates on arXiv.org · 40d ago Productionized Fairness Measurement Under Privacy Constraints cs.LG updates on arXiv.org · 40d ago Quantum Generative Diffusion Model for Real-World Time Series cs.LG updates on arXiv.org · 40d ago hia-gat: A Heterogeneous Interaction-Aware Graph Attention Network For Frame-Level Traffic Conflict Risk Prediction On Freeways cs.LG updates on arXiv.org · 40d ago PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration cs.LG updates on arXiv.org · 40d ago Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF cs.LG updates on arXiv.org · 40d ago Global Explanations for Multivariate Time Series Forecasting Models via $K$-Order Markov Approximations cs.LG updates on arXiv.org · 40d ago Training Observable Control Policies to Expose Agent State Through Actions cs.LG updates on arXiv.org · 40d ago COOPA: A Modular LLM Agent Architecture for Operations Research Problems cs.LG updates on arXiv.org · 40d ago FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks cs.LG updates on arXiv.org · 40d ago HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models cs.LG updates on arXiv.org · 40d ago Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis cs.LG updates on arXiv.org · 40d ago Directed Graph Topology Inference via Graph Filter Identification stat.ML updates on arXiv.org · 40d ago The Decision Geometry of Covariance Estimation for the Global Minimum-Variance Portfolio under Heavy Tails stat.ML updates on arXiv.org · 40d ago Adversarial Contamination Meets Hard Thresholding: An Iterative Algorithm with Signal Adaptivity and Minimax Optimality stat.ML updates on arXiv.org · 40d ago Local Fokker--Planck Geometry for Score Estimation: Heat-Ball Mean-Value Representations and Exact High-Dimensional Sampling stat.ML updates on arXiv.org · 40d ago Surprises in Proper Positive-Only Learning stat.ML updates on arXiv.org · 40d ago Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings stat.ML updates on arXiv.org · 40d ago Dangerous Liaisons of Convex Learning and Non-Affine Aggregation stat.ML updates on arXiv.org · 40d ago Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts stat.ML updates on arXiv.org · 40d ago How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks stat.ML updates on arXiv.org · 40d ago VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing stat.ML updates on arXiv.org · 40d ago Towards Reliable Recommender Systems for Rating Data stat.ML updates on arXiv.org · 40d ago Supervised Quadratic Feature Analysis: Information Geometry Approach for Dimensionality Reduction stat.ML updates on arXiv.org · 40d ago Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models stat.ML updates on arXiv.org · 40d ago Non-Linear Model-Based Sequential Decision-Making in Agriculture stat.ML updates on arXiv.org · 40d ago Self-Concordant Perturbations for Linear Bandits stat.ML updates on arXiv.org · 40d ago Trustworthy Predictive Distributions for Tail Events with Semiparametric Diagnostic Transport Maps stat.ML updates on arXiv.org · 40d ago Deep Residual Networks Learn the Geodesic Curve in the Wasserstein Space stat.ML updates on arXiv.org · 40d ago Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding stat.ML updates on arXiv.org · 40d ago Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction The latest research from Google · 42d ago LLMs help robots understand vague instructions and focus on key details MIT News - Machine learning · 42d ago Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics cs.LG updates on arXiv.org · 43d ago \chisao{}: A GPU-Native Parallel Optimizer for Multimodal Black-Box Functions via Convergence-Anticonvergence Oscillation cs.LG updates on arXiv.org · 43d ago Implementation of reinforcement learning in chemical reaction networks: application to phototaxis as curiosity-driven exploration cs.LG updates on arXiv.org · 43d ago Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis cs.LG updates on arXiv.org · 43d ago KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction cs.LG updates on arXiv.org · 43d ago Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations cs.LG updates on arXiv.org · 43d ago Clue-Guided Money Laundering Group Discovery cs.LG updates on arXiv.org · 43d ago Federated Hash Projected Latent Factor Learning cs.LG updates on arXiv.org · 43d ago Statistical and Structural Approaches to Algorithmic Fairness cs.LG updates on arXiv.org · 43d ago Topology-Informed Neural Networks for Flood Detection in Optical and Synthetic Aperture Radar Imagery cs.LG updates on arXiv.org · 43d ago A General Framework for Learning Algebraic Properties from Cayley Graphs using Graph Neural Networks cs.LG updates on arXiv.org · 43d ago Fast LeWorldModel cs.LG updates on arXiv.org · 43d ago Dataset Usage Inference without Shadow Models or Held-out Data cs.LG updates on arXiv.org · 43d ago Equivariance and Augmentation for Bayesian Neural Networks cs.LG updates on arXiv.org · 43d ago SSM Adapters via Hankel Reduced-order Modeling: Injection Site Determines Task Suitability in Long-Context Fine-Tuning cs.LG updates on arXiv.org · 43d ago The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators cs.LG updates on arXiv.org · 43d ago High-Probability PL-SGD with Markovian Noise: Optimal Mixing and Tail Dependence cs.LG updates on arXiv.org · 43d ago EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning cs.LG updates on arXiv.org · 43d ago Mesh-RL: Coupled subgrid reinforcement learning cs.LG updates on arXiv.org · 43d ago EMA-FS: Accelerating GBDT Training via Gain-Informed Feature Screening cs.LG updates on arXiv.org · 43d ago The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples stat.ML updates on arXiv.org · 43d ago A probabilistic framework for online test-time adaptation stat.ML updates on arXiv.org · 43d ago XMSE-Aware Adaptive Empirical Bayes Estimation stat.ML updates on arXiv.org · 43d ago Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference stat.ML updates on arXiv.org · 43d ago Ribbon: Scalable Approximation and Robust Uncertainty Quantification stat.ML updates on arXiv.org · 43d ago When are likely answers right? On Sequence Probability and Correctness in LLMs stat.ML updates on arXiv.org · 43d ago Statistical and Structural Approaches to Algorithmic Fairness stat.ML updates on arXiv.org · 43d ago Explainable Outlier Detection for Interval-valued Data stat.ML updates on arXiv.org · 43d ago Learning Probabilistic Filters with Strictly Proper Scoring Rules stat.ML updates on arXiv.org · 43d ago $\lambda$-PSD: Scalable Approximate SNR-Optimised Polynomial Stein Discrepancies stat.ML updates on arXiv.org · 43d ago Scalable Operator Learning via Nystr\"om Approximation With Denoising Applications stat.ML updates on arXiv.org · 43d ago Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork stat.ML updates on arXiv.org · 43d ago Data-Driven Duration Management -- Term Structure Forecasting Using Machine Learning stat.ML updates on arXiv.org · 43d ago Asymptotically Optimal Learning for Parametric Prophet Inequalities stat.ML updates on arXiv.org · 43d ago Decision-Aligned Evaluation of Uncertainty Quantification stat.ML updates on arXiv.org · 43d ago The Geometry of Updates: Fisher Alignment at Vocabulary Scale stat.ML updates on arXiv.org · 43d ago Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity stat.ML updates on arXiv.org · 43d ago All you need is log stat.ML updates on arXiv.org · 43d ago No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference stat.ML updates on arXiv.org · 43d ago Theory of the Frequency Principle for General Deep Neural Networks stat.ML updates on arXiv.org · 43d ago Understanding the brain with AI-driven explanations and experiments Microsoft Research · 43d ago Optimizing cloud economics with linear elastic caching The latest research from Google · 44d ago Which tokens does a hybrid model predict better? Ai2 Blog · 44d ago Dense Supervision Is Not Enough: The Readout Blind Spot in Looped Language Models cs.LG updates on arXiv.org · 44d ago From Meta Idea to Advanced Mathematical Discovery -- Human-AI Co-Discovery of Sign-Embedding Quantum Algorithms cs.LG updates on arXiv.org · 44d ago On-Device Neural Architecture Search cs.LG updates on arXiv.org · 44d ago LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning cs.LG updates on arXiv.org · 44d ago A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis cs.LG updates on arXiv.org · 44d ago When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models cs.LG updates on arXiv.org · 44d ago Conformal Orbit-Valid Trust Horizons for Equivariant World Models cs.LG updates on arXiv.org · 44d ago Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources cs.LG updates on arXiv.org · 44d ago Holographic Memory for Zero-Shot Compositional Reasoning in Knowledge Graphs: A Mechanistic Study of Where and Why It Fails cs.LG updates on arXiv.org · 44d ago MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios cs.LG updates on arXiv.org · 44d ago How Complexity Contributes to Learning Opacity in Machine Learning cs.LG updates on arXiv.org · 44d ago Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity cs.LG updates on arXiv.org · 44d ago Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series cs.LG updates on arXiv.org · 44d ago Convex--Concave Quadratic Spectral Filtering for Graph Neural Networks cs.LG updates on arXiv.org · 44d ago Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems cs.LG updates on arXiv.org · 44d ago Reliable Conformal Prediction for Ordinal Classification Using the Ranked Probability Score cs.LG updates on arXiv.org · 44d ago Enhancing Clinician Decision-Making via Uncertainty-Aware Multi-Expert Fusion for Stroke Rehabilitation cs.LG updates on arXiv.org · 44d ago Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models cs.LG updates on arXiv.org · 44d ago Evidence for feature-specific error correction in LLMs cs.LG updates on arXiv.org · 44d ago Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach cs.LG updates on arXiv.org · 44d ago Minimax PAC Bounds for Learning in Exogenous Contextual MDPs stat.ML updates on arXiv.org · 44d ago Stabilizing black-box algorithms through task-oriented randomization stat.ML updates on arXiv.org · 44d ago Statistically Valid Hyperparameter Selection: From Tuning to Guarantees stat.ML updates on arXiv.org · 44d ago Gaussian Mean Field Variational Inference can Overestimate Predictive Variance stat.ML updates on arXiv.org · 44d ago FedReLa: Imbalanced Federated Learning via Re-Labeling stat.ML updates on arXiv.org · 44d ago When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification? stat.ML updates on arXiv.org · 44d ago A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging stat.ML updates on arXiv.org · 44d ago Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation stat.ML updates on arXiv.org · 44d ago Information from coincidences stat.ML updates on arXiv.org · 44d ago Hierarchical Partial-Order Models for Ranking stat.ML updates on arXiv.org · 44d ago Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models stat.ML updates on arXiv.org · 44d ago Efficient Adaptive Data Acquisition via Pretrained Belief Representations stat.ML updates on arXiv.org · 44d ago Learning Interpretable Text Signals for Structured Responses stat.ML updates on arXiv.org · 44d ago A functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting stat.ML updates on arXiv.org · 44d ago Deviance-style normalization for jointly overdispersed counts stat.ML updates on arXiv.org · 44d ago Robust Linear Predictions: Analyses of Uniform Concentration, Fast Rates and Model Misspecification stat.ML updates on arXiv.org · 44d ago Structured Approximations of Measures stat.ML updates on arXiv.org · 44d ago Adaptive Cumulative Mass Calibration with Conformal Prediction stat.ML updates on arXiv.org · 44d ago Symmetric Linear Dynamical Systems are Learnable from Few Observations stat.ML updates on arXiv.org · 44d ago Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data stat.ML updates on arXiv.org · 44d ago Improving the speed and energy-efficiency of AI agents MIT News - Machine learning · 44d ago The fuel of the future is already here: Why TRISO matters Amazon Science homepage · 44d ago Thinking to recall: How reasoning unlocks parametric knowledge in LLMs The latest research from Google · 44d ago Introducing computer use in Gemini 3.5 Flash Google DeepMind News · 44d ago Talos: Scaling rare disease diagnosis with automated, iterative genomic reanalysis Microsoft Research · 44d ago Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search cs.LG updates on arXiv.org · 45d ago Weight-Space Geometry of Offline Reasoning Training cs.LG updates on arXiv.org · 45d ago A Survey on Federated Causal Discovery and Inference cs.LG updates on arXiv.org · 45d ago Low-power analogue neural networks with trainable nonlinear connections for continuous control cs.LG updates on arXiv.org · 45d ago Synergizing Physically Constrained MCMC and Chemical-Informed Gaussian Processes for Reaction Network Discovery cs.LG updates on arXiv.org · 45d ago Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios cs.LG updates on arXiv.org · 45d ago One Ruler: A Same-Hands Re-Evaluation of Bivariate Causal Direction on Tuebingen, with a Parameter-Free Compression Baseline cs.LG updates on arXiv.org · 45d ago Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction cs.LG updates on arXiv.org · 45d ago Reconstructing GRACE Terrestrial Water Storage with Spatio-Temporal Graph Neural Networks: An Application to South America cs.LG updates on arXiv.org · 45d ago The Degeneracy Distillery cs.LG updates on arXiv.org · 45d ago Machine Learning Modeling for Real-Time Melt Pool Monitoring in Laser Powder Bed Fusion Additive Manufacturing: A Hybrid Approach cs.LG updates on arXiv.org · 45d ago Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning cs.LG updates on arXiv.org · 45d ago Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications cs.LG updates on arXiv.org · 45d ago Exact Schur-Sylvester Dimensionality Reductions for Non-Smooth Stochastic Complexity and Manifold Sampling cs.LG updates on arXiv.org · 45d ago Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data cs.LG updates on arXiv.org · 45d ago MGI: Member vs Generated Inference cs.LG updates on arXiv.org · 45d ago GRACE: Gated Refinement for Accurate Causal Edge Discovery in High-Dimensional Time Series cs.LG updates on arXiv.org · 45d ago ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation cs.LG updates on arXiv.org · 45d ago Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI cs.LG updates on arXiv.org · 45d ago Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate cs.LG updates on arXiv.org · 45d ago Automated Residual Plot Assessment With the R Package autovi and the Shiny Application autovi.web stat.ML updates on arXiv.org · 45d ago Model selection with proper scoring rules on data sets of time series stat.ML updates on arXiv.org · 45d ago The Degeneracy Distillery stat.ML updates on arXiv.org · 45d ago Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data stat.ML updates on arXiv.org · 45d ago Stochastic Expectation Maximization for Robust State-Space Radio Interferometric Imaging stat.ML updates on arXiv.org · 45d ago A Dual Edge Spatial Jacobian Image Graph for Interpretable Diabetic Retinopathy Grading stat.ML updates on arXiv.org · 45d ago When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews stat.ML updates on arXiv.org · 45d ago A Step Towards Inherently Interpretable Causal Machine Learning Models For Decision Support stat.ML updates on arXiv.org · 45d ago Data Augmentation: A Fourier Analysis Perspective stat.ML updates on arXiv.org · 45d ago NoLimits.jl: Flexible and Composable Nonlinear Mixed-Effects Modeling in Julia stat.ML updates on arXiv.org · 45d ago History estimation in random recursive trees: Pointwise approach via iterated Jordan centralities stat.ML updates on arXiv.org · 45d ago A Differentially Private Weighted Empirical Risk Minimization Procedure and its Application to Outcome Weighted Learning stat.ML updates on arXiv.org · 45d ago Predictive variational inference: Learn the predictively optimal posterior distribution stat.ML updates on arXiv.org · 45d ago LLMs are Bayesian, In Expectation, Not in Realization stat.ML updates on arXiv.org · 45d ago An adaptive subsampling method for large-sample feature screening stat.ML updates on arXiv.org · 45d ago Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning stat.ML updates on arXiv.org · 45d ago Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces stat.ML updates on arXiv.org · 45d ago Evaluation Metrics as Averaged Outcomes of Fair Gambles stat.ML updates on arXiv.org · 45d ago Towards CSI-Native Foundation Models: A Channel-Adaptive Roadmap for 6G cs.LG updates on arXiv.org · 46d ago NeuroShield: A Device-Agnostic Foundation Model for EEG Authentication cs.LG updates on arXiv.org · 46d ago Massive Activations Are Architecturally Robust: A Controlled Scratch/Commitment Residual Stream Test cs.LG updates on arXiv.org · 46d ago CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks cs.LG updates on arXiv.org · 46d ago Evidential Fusion Network for Multimodal Survival Prediction under Missing Modalities cs.LG updates on arXiv.org · 46d ago ELADO: Elliptic PDE Assessment Datasets for Operator Learning cs.LG updates on arXiv.org · 46d ago B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet cs.LG updates on arXiv.org · 46d ago CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes cs.LG updates on arXiv.org · 46d ago Evolutionary Discovery of Developmental Reward Schedules in Deep Reinforcement Learning cs.LG updates on arXiv.org · 46d ago Machine Learning Classification of Cryopathy Syndromes: A Comprehensive Comparative Study cs.LG updates on arXiv.org · 46d ago Understanding Latent Flow Models for Tabular Data Synthesis: Targets, Paths, and Sampling cs.LG updates on arXiv.org · 46d ago Temporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals cs.LG updates on arXiv.org · 46d ago MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction cs.LG updates on arXiv.org · 46d ago Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels cs.LG updates on arXiv.org · 46d ago Short-Term Electricity Demand Forecasting for New England Using a Hybrid Transformer-XGBoost Framework with Weather, Calendar, and COVID-19 Indicators cs.LG updates on arXiv.org · 46d ago $\Omega$: Operator-based Mixture Ensemble for Generative Assimilation cs.LG updates on arXiv.org · 46d ago Hierarchical Pooling for Sheaf Neural Networks cs.LG updates on arXiv.org · 46d ago Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study cs.LG updates on arXiv.org · 46d ago Learning through Internalization cs.LG updates on arXiv.org · 46d ago Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention cs.LG updates on arXiv.org · 46d ago Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components stat.ML updates on arXiv.org · 46d ago Betting on Moments: Legendre Jumper Martingales for Online Exchangeability Testing stat.ML updates on arXiv.org · 46d ago Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning stat.ML updates on arXiv.org · 46d ago Diffusion-Driven State Space Models stat.ML updates on arXiv.org · 46d ago Bayesian Model Averaging under Predictor Redundancy via Density-Ratio Posterior Compression stat.ML updates on arXiv.org · 46d ago Two Layers of Instability in Causal Estimation stat.ML updates on arXiv.org · 46d ago Orthogonal Discrepancy Kernels for Learning with Partial Physics stat.ML updates on arXiv.org · 46d ago Subsampling for supervised learning in reproducing kernel Hilbert spaces stat.ML updates on arXiv.org · 46d ago Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design stat.ML updates on arXiv.org · 46d ago Signed Evidence Flow: Conflict-Aware and Stability-Calibrated Data Analysis stat.ML updates on arXiv.org · 46d ago Variance-Tilted Diffusion Models for Diverse Sampling stat.ML updates on arXiv.org · 46d ago Convergence Analysis of Nystr\"om Subsampling in Covariate Shift Adaptation for Misspecified case stat.ML updates on arXiv.org · 46d ago Null-Calibrated Conformal Selection via Target-Membership Scores stat.ML updates on arXiv.org · 46d ago Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems stat.ML updates on arXiv.org · 46d ago Robust Diffusion Models via Divergence-Induced Weighted Denoising stat.ML updates on arXiv.org · 46d ago Scalable Bayesian Additive Models for Stellar Flare Detection via Amortized Gaussian Process Inference and Hidden Markov Models stat.ML updates on arXiv.org · 46d ago Statistical Inference for Misspecified Contextual Bandits stat.ML updates on arXiv.org · 46d ago Data Evolution by Wittgenstein's Rule Following stat.ML updates on arXiv.org · 46d ago Domain Adaptation Under Wireless Network Constraints: When Does It Become Green? stat.ML updates on arXiv.org · 46d ago Time Series Classification through Diffeomorphic Time Warping (DiffTW) stat.ML updates on arXiv.org · 46d ago New chip could help tiny robots traverse complex environments MIT News - Machine learning · 46d ago A better way to model the behavior of metal alloys MIT News - Machine learning · 49d ago Healthcare Benchmarks Are Only as Good as Their Assumptions Machine Learning Blog | ML@CMU | Carnegie Mellon University · 49d ago Should AIs be people too? Future of Life Institute · 49d ago Computational Identifiability cs.LG updates on arXiv.org · 50d ago When to Trust, How to Distill: Multi-Foundation Model Guidance for Lightweight, Robust Scientific Time Series Forecasting cs.LG updates on arXiv.org · 50d ago Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM Inference cs.LG updates on arXiv.org · 50d ago Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures cs.LG updates on arXiv.org · 50d ago Information Lattice Learning as Probabilistic Graphical Model Structure Learning cs.LG updates on arXiv.org · 50d ago Weibull Weight-Scale Parameter Evolution under AdamW Training Dynamics cs.LG updates on arXiv.org · 50d ago Zero-Inflated Gaussian Distributions Enable Parameter-Space Sparsity in Estimation-of-Distribution Algorithms cs.LG updates on arXiv.org · 50d ago Human-like autonomy emerges from self-play and a pinch of human data cs.LG updates on arXiv.org · 50d ago ProMUSE: Progressive Multi-modal Uncertainty-guided Staged Evidential Alzheimer Disease Classification cs.LG updates on arXiv.org · 50d ago cAPM: Continual AI-Assisted Pace-Mapping with Active Learning cs.LG updates on arXiv.org · 50d ago Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs cs.LG updates on arXiv.org · 50d ago Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations cs.LG updates on arXiv.org · 50d ago Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees cs.LG updates on arXiv.org · 50d ago Emyx: Fast and efficient all-atom protein generation cs.LG updates on arXiv.org · 50d ago A Hybrid GNN-FEM Framework for Phase-Field Fracture Simulation. Physics-Preserving Hybridization for Generalizable Surrogate Modeling cs.LG updates on arXiv.org · 50d ago How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural cs.LG updates on arXiv.org · 50d ago VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving cs.LG updates on arXiv.org · 50d ago Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models cs.LG updates on arXiv.org · 50d ago FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning cs.LG updates on arXiv.org · 50d ago Spectral DPPs via NEPv: A Scalable Continuous Relaxation of Determinantal MAP for Diversity-Aware Data Selection cs.LG updates on arXiv.org · 50d ago The Representational Limit of Scalar Interactions: An Interventional Decomposition stat.ML updates on arXiv.org · 50d ago A Solver-Free Training Method for Predict-then-Optimize stat.ML updates on arXiv.org · 50d ago Variational Consensus Monte Carlo for Bayesian Mixture stat.ML updates on arXiv.org · 50d ago AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing stat.ML updates on arXiv.org · 50d ago Stochastic Linear Contextual Bandits with Bounded Noise: A Set-Membership Approach stat.ML updates on arXiv.org · 50d ago AK-MCS-C2 : Active Kriging Monte Carlo Simulation method with conformal certification for failure probability estimation stat.ML updates on arXiv.org · 50d ago Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random stat.ML updates on arXiv.org · 50d ago Statistical Properties of Training & Generalization stat.ML updates on arXiv.org · 50d ago SSH-Net: A Deep Neural Network for Predicting Failure Time Distribution Functions under Competing Risks with Application to GPU Data stat.ML updates on arXiv.org · 50d ago Computational Identifiability stat.ML updates on arXiv.org · 50d ago Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale stat.ML updates on arXiv.org · 50d ago Overfitted high-dimensional matrix factorizations via adaptive spectral shrinkage stat.ML updates on arXiv.org · 50d ago Machine Learning Integrated in Wavelet Shrinkage (MLShrink) stat.ML updates on arXiv.org · 50d ago Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction stat.ML updates on arXiv.org · 50d ago Calibration without labels in multiple testing stat.ML updates on arXiv.org · 50d ago On the Oracle Complexity of Interpolation-Based Gradient Descent stat.ML updates on arXiv.org · 50d ago Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning stat.ML updates on arXiv.org · 50d ago Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise stat.ML updates on arXiv.org · 50d ago Leveraging tails for adaptation stat.ML updates on arXiv.org · 50d ago Optimal Deterministic Multicalibration and Omniprediction stat.ML updates on arXiv.org · 50d ago How Domyn and AISquared built on Ai2's open releases Ai2 Blog · 51d ago Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing cs.LG updates on arXiv.org · 51d ago Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier cs.LG updates on arXiv.org · 51d ago CODEBLOCK: Learning to Supervise Code at the Right Granularity cs.LG updates on arXiv.org · 51d ago Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS cs.LG updates on arXiv.org · 51d ago A Link between Shock-wave Theory and Symmetry-reduced Stochastic Gradient Descent for Artificial Neural Networks cs.LG updates on arXiv.org · 51d ago Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression cs.LG updates on arXiv.org · 51d ago Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds cs.LG updates on arXiv.org · 51d ago DRIFT: Refining Instruction Data via On-Policy Data Attribution cs.LG updates on arXiv.org · 51d ago TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning cs.LG updates on arXiv.org · 51d ago SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector cs.LG updates on arXiv.org · 51d ago Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation cs.LG updates on arXiv.org · 51d ago A Survey on Data-Driven Models for Soil Moisture Regression and Classification cs.LG updates on arXiv.org · 51d ago Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion cs.LG updates on arXiv.org · 51d ago ASTRA: A Scalable Next-Generation ATCO Training Simulator with Autonomous Simpilots cs.LG updates on arXiv.org · 51d ago SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior cs.LG updates on arXiv.org · 51d ago Why SWAVE May Not Be All You Need:A Concept-Evolution Retrospective on Complex-Valued Recurrent Language Models cs.LG updates on arXiv.org · 51d ago Neural Network Implementation of the Renormalization Group for Fault Diagnosis with Class Imbalance cs.LG updates on arXiv.org · 51d ago Self-CTRL: Self-Consistency Training with Reinforcement Learning cs.LG updates on arXiv.org · 51d ago ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets cs.LG updates on arXiv.org · 51d ago Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting cs.LG updates on arXiv.org · 51d ago Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks stat.ML updates on arXiv.org · 51d ago ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift stat.ML updates on arXiv.org · 51d ago Compact Geometric Representations of Hierarchies stat.ML updates on arXiv.org · 51d ago Toward Simultaneously Optimal Regret in U-Calibration stat.ML updates on arXiv.org · 51d ago When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? stat.ML updates on arXiv.org · 51d ago Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies stat.ML updates on arXiv.org · 51d ago TimeLAVA: Learning-Agnostic Data Valuation for Time Series stat.ML updates on arXiv.org · 51d ago Kernel of Partition Paths: A Unified Representation for Tree Ensembles stat.ML updates on arXiv.org · 51d ago FOSC-X: An Extended Framework for Optimal Local Cuts and Non-Horizontal Cluster Selection from Clustering Hierarchies stat.ML updates on arXiv.org · 51d ago Sequential Kernel-based Conditional Independence Testing via Adaptive Betting stat.ML updates on arXiv.org · 51d ago Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning stat.ML updates on arXiv.org · 51d ago On Local Population-Risk Certificates stat.ML updates on arXiv.org · 51d ago Generalised Eigenvalue Geometry of Semantic Adversarial Attacks stat.ML updates on arXiv.org · 51d ago The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient stat.ML updates on arXiv.org · 51d ago A Guide to Estimating Conditional Average Treatment Effects in Competing Risks Settings stat.ML updates on arXiv.org · 51d ago Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds stat.ML updates on arXiv.org · 51d ago Bayesian Nonparametric Detection of Anomalies in Multivariate Functional Data stat.ML updates on arXiv.org · 51d ago Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction stat.ML updates on arXiv.org · 51d ago Mixed-Precision Communication-Avoiding SGD for Generalized Linear Models on GPUs stat.ML updates on arXiv.org · 51d ago Quantum Annealing Enhanced Reinforcement Learning for Accurate Remaining Useful Lifetime Prediction stat.ML updates on arXiv.org · 51d ago In game theory, generalists sometimes win out over specialists MIT News - Machine learning · 51d ago MolmoMotion: Language-guided 3D motion forecasting Ai2 Blog · 52d ago Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs cs.LG updates on arXiv.org · 52d ago Diagnosing and Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry cs.LG updates on arXiv.org · 52d ago Informative Missingness to Generate Irregular Clinical Time Series cs.LG updates on arXiv.org · 52d ago Models Take Notes at Prefill: KV Cache Can Be Editable and Composable cs.LG updates on arXiv.org · 52d ago The Critical Role of Model Selection in Causal Inference: A Comparative Analysis of Classification Models within the InferBERT Framework for Pharmacovigilance cs.LG updates on arXiv.org · 52d ago Probing, Fusion, and Trustworthiness: A Systematic Evaluation of Foundation Model Representations for Multimodal Cancer Analysis cs.LG updates on arXiv.org · 52d ago MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs cs.LG updates on arXiv.org · 52d ago Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks cs.LG updates on arXiv.org · 52d ago Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations cs.LG updates on arXiv.org · 52d ago Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems cs.LG updates on arXiv.org · 52d ago Finsler Geometry, Graph Neural Networks, and You cs.LG updates on arXiv.org · 52d ago Constrained Diffusion Models with Primal-Dual Inference cs.LG updates on arXiv.org · 52d ago PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation cs.LG updates on arXiv.org · 52d ago Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization cs.LG updates on arXiv.org · 52d ago Rift: A Conflict Signature for Deception in Language Models cs.LG updates on arXiv.org · 52d ago Uncertainty Quantification of Engineering Structures by Polynomial Chaos Expansion and Multivariate Active Learning cs.LG updates on arXiv.org · 52d ago Rethinking Groups in Critic-Free RLVR cs.LG updates on arXiv.org · 52d ago ProCUA-SFT Technical Report cs.LG updates on arXiv.org · 52d ago Decision-Driven Geosteering Under Uncertainty: A Unified Framework for Sequential Decision Optimization cs.LG updates on arXiv.org · 52d ago Counterfactual Optimization of Baseball Pitch Sequences and Estimation of Its Impact on Season-Level Statistics cs.LG updates on arXiv.org · 52d ago Another Look at Log-PCA for Probability Measures: A Dynamical Formulation and Statistical Convergence stat.ML updates on arXiv.org · 52d ago Tight $L_\infty$ Sample Complexity for Low-Degree and Sparse Boolean Polynomials stat.ML updates on arXiv.org · 52d ago Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty stat.ML updates on arXiv.org · 52d ago A Bayesian Boolean Matrix Factorization with Application to Copy Number Analysis in Cancer stat.ML updates on arXiv.org · 52d ago Geometrical fairness in graph neural networks stat.ML updates on arXiv.org · 52d ago Differential Privacy of Gaussian Process Posterior Sampling stat.ML updates on arXiv.org · 52d ago Fast Nonparametric Conditional Independence Testing via Two-Stage Regression stat.ML updates on arXiv.org · 52d ago Tensor-based second-order causal discovery stat.ML updates on arXiv.org · 52d ago A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise stat.ML updates on arXiv.org · 52d ago Finsler Geometry, Graph Neural Networks, and You stat.ML updates on arXiv.org · 52d ago Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization stat.ML updates on arXiv.org · 52d ago Uncertainty Quantification of Engineering Structures by Polynomial Chaos Expansion and Multivariate Active Learning stat.ML updates on arXiv.org · 52d ago Accelerated Convex Optimization via Hamiltonian Dynamics with Deterministic Integration Time stat.ML updates on arXiv.org · 52d ago Bayesian Poisson-Randomized Gamma Tensor Factorization with Application to International Trade Flows stat.ML updates on arXiv.org · 52d ago Kernel-Based Functional Balancing for Causal Inference with Compositional Treatments stat.ML updates on arXiv.org · 52d ago A Polyak-Ruppert Central Limit Theorem for SA-Adam with Momentum and Non-Convergent Adaptive Preconditioning stat.ML updates on arXiv.org · 52d ago Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy Validation stat.ML updates on arXiv.org · 52d ago Martingale Doppelg\"anger-Eval: An Identification Framework for Auditing Candlestick Understanding in Vision-Language Models stat.ML updates on arXiv.org · 52d ago Anytime-valid Optimal Policy Identification stat.ML updates on arXiv.org · 52d ago FoundCause: Causal Discovery with Latent Confounders from Observational Data stat.ML updates on arXiv.org · 52d ago Could AI tell you where you left your keys? MIT News - Machine learning · 52d ago Unlocking UK house-building with AI-accelerated planning Google DeepMind News · 52d ago From pixels to planning: Earth AI for nature restoration The latest research from Google · 52d ago Securing the future of AI agents Google DeepMind News · 52d ago QPILOTS: Efficient Test-Time Q-Steering for Flow Policies cs.LG updates on arXiv.org · 53d ago GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness cs.LG updates on arXiv.org · 53d ago {\alpha}-Fair Insurance Pricing: A Fairness Continuum cs.LG updates on arXiv.org · 53d ago GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning cs.LG updates on arXiv.org · 53d ago Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts cs.LG updates on arXiv.org · 53d ago Separable Neural Architectures as Physical World Models: from Mathematical Theory to Applications cs.LG updates on arXiv.org · 53d ago Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation cs.LG updates on arXiv.org · 53d ago A Comparative Study of Graph Neural Network Layer Selection for Interaction Modelling in Driving Trajectory Prediction cs.LG updates on arXiv.org · 53d ago Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning cs.LG updates on arXiv.org · 53d ago Benchmarking Instance-Dependent Label Noise with Controlled Corruptions cs.LG updates on arXiv.org · 53d ago Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning cs.LG updates on arXiv.org · 53d ago FastMix: Fast Data Mixture Optimization via Gradient Descent cs.LG updates on arXiv.org · 53d ago Rational Sparse Autoencoder cs.LG updates on arXiv.org · 53d ago Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders cs.LG updates on arXiv.org · 53d ago How Should World Models Be Evaluated? A Decision-Making-Centric Position cs.LG updates on arXiv.org · 53d ago Transformers Learn the Mestre-Nagao Heuristic cs.LG updates on arXiv.org · 53d ago Temporal Difference Learning for Diffusion Models cs.LG updates on arXiv.org · 53d ago Physics-conforming Latent Twins cs.LG updates on arXiv.org · 53d ago Size Doesn't Matter: Cosine-Scored Sparse Autoencoders cs.LG updates on arXiv.org · 53d ago Machine Learning and the Random Walk Puzzle: Forecasting the CAD/USD Exchange Rate with Expanding Window Evaluation and SHAP Interpretability cs.LG updates on arXiv.org · 53d ago Audited Conformal Prediction for Classification under Unknown Distribution Shift stat.ML updates on arXiv.org · 53d ago Conformal Candidate Certification for Offline Model-Based Optimization stat.ML updates on arXiv.org · 53d ago Finite Resources False Discovery Rate Control in Structured Hypothesis Spaces stat.ML updates on arXiv.org · 53d ago The Reverse Telescoping Coordinate System for Positive Definite Matrices: Geometry, Computation, and Generative Modeling stat.ML updates on arXiv.org · 53d ago Structured Nonparametric Variational Inference for Dependent Latent Modeling stat.ML updates on arXiv.org · 53d ago Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow stat.ML updates on arXiv.org · 53d ago Phase Transition in Convex Relaxations for Graph Alignment stat.ML updates on arXiv.org · 53d ago Information Gap and Feasibility-Aware Inference in Binomial Logistic Mixtures stat.ML updates on arXiv.org · 53d ago Stochastic trace estimation with tensor train random vectors stat.ML updates on arXiv.org · 53d ago Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data stat.ML updates on arXiv.org · 53d ago PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift stat.ML updates on arXiv.org · 53d ago Closing the Approximation Gap in Simulation-free Latent SDEs stat.ML updates on arXiv.org · 53d ago Generative Modeling on Metric Graphs via Neural Optimal Transport stat.ML updates on arXiv.org · 53d ago Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees stat.ML updates on arXiv.org · 53d ago Attention is Just Another Name for Coupling?: A Fast-Slow ODE Perspective on Hierarchical Pretraining stat.ML updates on arXiv.org · 53d ago A nonparametric two-sample test using a parametric integral probability metric stat.ML updates on arXiv.org · 53d ago Sobolev Approximation by Fixed-Size Neural Networks with Arbitrary Accuracy stat.ML updates on arXiv.org · 53d ago Dynestyx: A Probabilistic Programming Library for Dynamical Systems stat.ML updates on arXiv.org · 53d ago Learning Topological Representations for Molecular Dynamics stat.ML updates on arXiv.org · 53d ago Bridging data-driven priors via the score function for posterior sampling -- Comparative review and experimental study stat.ML updates on arXiv.org · 53d ago Can Editing 1 Neuron Fix Repetition Loops in LLMs? cs.LG updates on arXiv.org · 54d ago Efficient On-Device Diffusion LLM Inference with Mobile NPU cs.LG updates on arXiv.org · 54d ago High-Frequency Pricing at Scale for E-Commerce cs.LG updates on arXiv.org · 54d ago A fully GPU-based workflow for building physics emulators of hypersonic flows cs.LG updates on arXiv.org · 54d ago FedSPC: Shared Parameter Correction for Personalized Federated Learning cs.LG updates on arXiv.org · 54d ago The Weight Norm Sets the Grokking Timescale: A Causal Delay Law cs.LG updates on arXiv.org · 54d ago D2H-AD: A Hybrid Model Utilizing Hyperdimensional Computing for Advanced Anomaly Detection cs.LG updates on arXiv.org · 54d ago Beyond LoRA: Is Sparsity-Induced Adaptation Better? cs.LG updates on arXiv.org · 54d ago Diffusion Policy Optimization without Drifting Apart cs.LG updates on arXiv.org · 54d ago Neural Variability Enhances Artificial Network Robustness cs.LG updates on arXiv.org · 54d ago Neural Slack Variables for Shape Constraints cs.LG updates on arXiv.org · 54d ago Uncertainty Estimation and Generalization Bounds for Modern Deep Learning cs.LG updates on arXiv.org · 54d ago Attention-Based Estimation of the Individual Treatment Benefit Probability under Dose Variation cs.LG updates on arXiv.org · 54d ago A Stationarity-and-Coupling Criterion for Training-Free Time-Lagged Spectral Embeddings of Multivariate Time Series cs.LG updates on arXiv.org · 54d ago SuperThoughts: Reasoning Tokens in Superposition cs.LG updates on arXiv.org · 54d ago Muon$^p$: Muon with Fractional Spectral Powers cs.LG updates on arXiv.org · 54d ago Natively Unlearnable Large Language Models cs.LG updates on arXiv.org · 54d ago A Longitudinal Attribute-Conditioned Neural Network for Modeling Health-State Transition Probabilities in Temporally Irregular Data: The LANTERN Framework cs.LG updates on arXiv.org · 54d ago Gefen: Optimized Stochastic Optimizer cs.LG updates on arXiv.org · 54d ago SpikF-GO: Spiking Fourier Graph Operators for Multivariate Time Series Forecasting cs.LG updates on arXiv.org · 54d ago LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models stat.ML updates on arXiv.org · 54d ago Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization stat.ML updates on arXiv.org · 54d ago Adaptive Nucleus Truncation for Long-Form Reasoning stat.ML updates on arXiv.org · 54d ago A General Framework for Decision Trees via Bregman Divergences stat.ML updates on arXiv.org · 54d ago Geometric Domain Adaptation via Optimal Transport for Linear Regression in R^2 stat.ML updates on arXiv.org · 54d ago Anytime-Valid Confirmation of Label-Shift Corrections stat.ML updates on arXiv.org · 54d ago Hybrid Uncertainty Sensitivity Analysis Based on the HSIC for High-Dimensional Responses with Aleatory--Epistemic Separation stat.ML updates on arXiv.org · 54d ago Gradient boosting for extremes: sampling theory and application to insurance stat.ML updates on arXiv.org · 54d ago Nonlocal Bayesian Modeling of Continuous Spatio-Temporal Dynamics stat.ML updates on arXiv.org · 54d ago Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias stat.ML updates on arXiv.org · 54d ago Cluster LOCO: Feature Importance For Interpreting Clusters stat.ML updates on arXiv.org · 54d ago A fully GPU-based workflow for building physics emulators of hypersonic flows stat.ML updates on arXiv.org · 54d ago Conformal calibration and look-elsewhere effect in anomaly detection for new-physics searches stat.ML updates on arXiv.org · 54d ago A Stationarity-and-Coupling Criterion for Training-Free Time-Lagged Spectral Embeddings of Multivariate Time Series stat.ML updates on arXiv.org · 54d ago Approximating Whittle-Matern Fields over Discretized Manifolds stat.ML updates on arXiv.org · 54d ago Controller-Augmented Hidden Markov Models: A Computational Framework for Constrained Sequential Inference stat.ML updates on arXiv.org · 54d ago Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs stat.ML updates on arXiv.org · 54d ago Temperature transferable Machine Learned Coarse Grained model for proteins stat.ML updates on arXiv.org · 54d ago Operator Calculus for Population-Based Optimization: A Mean-Field Convergence Theory stat.ML updates on arXiv.org · 54d ago Local Coverage Governs Memorization in Diffusion Models stat.ML updates on arXiv.org · 54d ago Research into how AI can help users understand skin conditions The latest research from Google · 56d ago A low-carbon computing platform from your retired phones The latest research from Google · 56d ago olmo-eval: An evaluation workbench for the model development loop Ai2 Blog · 57d ago Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency stat.ML updates on arXiv.org · 57d ago Epistemic Uncertainty Is Not the Reducible Kind stat.ML updates on arXiv.org · 57d ago Prediction-Powered Causal Inference by Automatic Debiased Machine Learning and Semi-Supervised Riesz Regression stat.ML updates on arXiv.org · 57d ago Robust State-Conditional Feature-Weighted Jump Models for Temporal Clustering stat.ML updates on arXiv.org · 57d ago ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization stat.ML updates on arXiv.org · 57d ago Simultaneous Latent Budget Trees for Stratified Classification stat.ML updates on arXiv.org · 57d ago Majority-of-Three is Optimal stat.ML updates on arXiv.org · 57d ago A Two-Parameter Weibull Framework for Diagnosing Transformer Weight Distributions stat.ML updates on arXiv.org · 57d ago Computationally tractable robust differentially private mean estimation stat.ML updates on arXiv.org · 57d ago Physics-Informed Neural Networks for Chemotherapy Pharmacokinetics: Benchmarking the Clinical Estimator and Exposing Parameter Identifiability stat.ML updates on arXiv.org · 57d ago How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings? stat.ML updates on arXiv.org · 57d ago Two-Layer Linear Auto-Regressive Models Estimate Latent States stat.ML updates on arXiv.org · 57d ago A unified complexity bound for logconcave sampling stat.ML updates on arXiv.org · 57d ago On McDiarmid's Inequality under Dependence via Approximate Tensorization of Entropy stat.ML updates on arXiv.org · 57d ago Diffusion-Network Alignment: An Efficient Algorithm and Explicit Probability Bounds stat.ML updates on arXiv.org · 57d ago Reliability of Probabilistic Emulation of Physical Systems stat.ML updates on arXiv.org · 57d ago A Quadratic Order Reduction -- Gaussian Process Ordinary Differential Equation framework for the inference of Large Continuous Dynamical Systems stat.ML updates on arXiv.org · 57d ago Calibrating simplified vine copulas with a noise contrastive estimation approach stat.ML updates on arXiv.org · 57d ago Towards More General Control of Diffusion Models Using Jeffrey Guidance stat.ML updates on arXiv.org · 57d ago REMAL: Residual Equilibrium Manifold Active Learning for Surrogate-Based Multidisciplinary Design Analysis stat.ML updates on arXiv.org · 57d ago When it comes to predicting people’s preferences, it pays to consider “the power of three” MIT News - Machine learning · 57d ago Restless bandits with imperfect binary feedback: PCL-indexability analysis and computation cs.LG updates on arXiv.org · 58d ago To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending cs.LG updates on arXiv.org · 58d ago Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention cs.LG updates on arXiv.org · 58d ago Few-Shot Resampling for Scalable Statistically-Sound Data Mining cs.LG updates on arXiv.org · 58d ago ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation cs.LG updates on arXiv.org · 58d ago Physics-informed generative AI for semiconductor manufacturing: Enforcing hard physical constraints in generative models by construction cs.LG updates on arXiv.org · 58d ago Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems cs.LG updates on arXiv.org · 58d ago Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization cs.LG updates on arXiv.org · 58d ago Loss Landscape Diagnosis for Gradient-Based Gray-Scott System Inversion: Disentangling the Roles of PINN Components cs.LG updates on arXiv.org · 58d ago PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry cs.LG updates on arXiv.org · 58d ago Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models cs.LG updates on arXiv.org · 58d ago A prior-free blind detection of information leakage from model predictions cs.LG updates on arXiv.org · 58d ago LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data cs.LG updates on arXiv.org · 58d ago Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation cs.LG updates on arXiv.org · 58d ago Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data cs.LG updates on arXiv.org · 58d ago RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways cs.LG updates on arXiv.org · 58d ago Least-Action-Guided Diffusion for Physical Extrapolation cs.LG updates on arXiv.org · 58d ago FreeBridge: Variational Schr\"odinger Bridges for Cellular Transition Dynamics cs.LG updates on arXiv.org · 58d ago FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse cs.LG updates on arXiv.org · 58d ago Learning from almost nothing: How neural networks survive heavy input corruption cs.LG updates on arXiv.org · 58d ago Annealed Entropic Allocation for Ranking and Selection stat.ML updates on arXiv.org · 58d ago Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records stat.ML updates on arXiv.org · 58d ago Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach stat.ML updates on arXiv.org · 58d ago Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation stat.ML updates on arXiv.org · 58d ago From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features stat.ML updates on arXiv.org · 58d ago Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence stat.ML updates on arXiv.org · 58d ago Fixed-Parameter Tractability of Private Synthetic Data Generation stat.ML updates on arXiv.org · 58d ago Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry stat.ML updates on arXiv.org · 58d ago GraphGP: Scalable Gaussian Processes with Vecchia's Approximation stat.ML updates on arXiv.org · 58d ago Signed Compression Progress on a Sealed Audit is Goodhart-Resistant stat.ML updates on arXiv.org · 58d ago The Power of Test-Time Training for Approximate Sampling stat.ML updates on arXiv.org · 58d ago CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching stat.ML updates on arXiv.org · 58d ago Unbiased Derivative Estimation for Stationary Mean of Parameterized Markov chains stat.ML updates on arXiv.org · 58d ago Continuous biome representations from Earth observation embeddings stat.ML updates on arXiv.org · 58d ago Range-Aware Bayesian Optimization for Discovering Diverse Designs within Target Property Windows stat.ML updates on arXiv.org · 58d ago Tree-Structured Orthonormal Decomposition of the Aitchison Simplex stat.ML updates on arXiv.org · 58d ago Capacity-Constrained Online Convex Optimization with Delayed Feedback stat.ML updates on arXiv.org · 58d ago Time Series Analysis in Machine Learning stat.ML updates on arXiv.org · 58d ago Magnitude-Based Features for Multispecies Spatial Data stat.ML updates on arXiv.org · 58d ago Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers stat.ML updates on arXiv.org · 58d ago New framework for auditing machine unlearning The latest research from Google · 58d ago DiffusionGemma: 4x faster text generation Google DeepMind News · 58d ago EC2’s formally verified “isolation engine” provides mathematical assurance of virtual-machine isolation Amazon Science homepage · 58d ago Graviton5’s improved design increases speed and energy efficiency — beyond Moore’s law Amazon Science homepage · 58d ago Investing in multi-agent AI safety research Google DeepMind News · 59d ago Mechanistic Analysis of Alignment Algorithms in Language Models cs.LG updates on arXiv.org · 59d ago SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning cs.LG updates on arXiv.org · 59d ago Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows cs.LG updates on arXiv.org · 59d ago Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding cs.LG updates on arXiv.org · 59d ago Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages cs.LG updates on arXiv.org · 59d ago Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models cs.LG updates on arXiv.org · 59d ago Blurry Window Attention cs.LG updates on arXiv.org · 59d ago From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents cs.LG updates on arXiv.org · 59d ago Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation cs.LG updates on arXiv.org · 59d ago LLM-as-a-Discriminator: When Synthetic Tables Still Look Real cs.LG updates on arXiv.org · 59d ago Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning cs.LG updates on arXiv.org · 59d ago SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs cs.LG updates on arXiv.org · 59d ago QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning cs.LG updates on arXiv.org · 59d ago PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks cs.LG updates on arXiv.org · 59d ago Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning cs.LG updates on arXiv.org · 59d ago Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection cs.LG updates on arXiv.org · 59d ago Integrating Local and Global Entropy for Uncertainty Quantification in LLMs cs.LG updates on arXiv.org · 59d ago Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs cs.LG updates on arXiv.org · 59d ago Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM Wikis cs.LG updates on arXiv.org · 59d ago FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses cs.LG updates on arXiv.org · 59d ago Convergence Rates for Neural-Network Estimation with Current-Status Data stat.ML updates on arXiv.org · 59d ago Robust Active Learning for Few-Shot Example Selection in Text-to-SQL stat.ML updates on arXiv.org · 59d ago Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising stat.ML updates on arXiv.org · 59d ago $k$-Nearest Neighbors in Gromov--Wasserstein Space stat.ML updates on arXiv.org · 59d ago Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin stat.ML updates on arXiv.org · 59d ago Human-AI Teaming Through the Lens of Calibration stat.ML updates on arXiv.org · 59d ago Range Penalization: Theoretical Insights with Applications in Federated Learning stat.ML updates on arXiv.org · 59d ago Generalized Conformal Predictive Systems Under Distributional Shifts stat.ML updates on arXiv.org · 59d ago It\^o maps for any-step SDEs stat.ML updates on arXiv.org · 59d ago Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models stat.ML updates on arXiv.org · 59d ago Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages stat.ML updates on arXiv.org · 59d ago Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection stat.ML updates on arXiv.org · 59d ago Integrating Local and Global Entropy for Uncertainty Quantification in LLMs stat.ML updates on arXiv.org · 59d ago TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts stat.ML updates on arXiv.org · 59d ago Nonlinear Estimator: Dual Bayesian Affine Estimators for Parameter Learning stat.ML updates on arXiv.org · 59d ago Intrinsic Footpoint-invariant Riemannian Cross-covariance stat.ML updates on arXiv.org · 59d ago Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks stat.ML updates on arXiv.org · 59d ago A Mean-Field Analysis of Multi-Head Self-Attention under Cross-Entropy Training stat.ML updates on arXiv.org · 59d ago Advancing the State-of-the-Art in Empirical Privacy Auditing stat.ML updates on arXiv.org · 59d ago Deterministic Denominator Design for Localized Tamed Stochastic-Gradient Langevin Dynamics stat.ML updates on arXiv.org · 59d ago Fluid, natural voice translation with Gemini 3.5 Live Translate Google DeepMind News · 59d ago Introducing Gemma 4 12B: a unified, encoder-free multimodal model Google DeepMind News · 59d ago Powering the future of robotics in Europe Google DeepMind News · 59d ago Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark cs.LG updates on arXiv.org · 60d ago MedicalRec: Medical recommender system for image classification without retraining cs.LG updates on arXiv.org · 60d ago SPIN: Decentralized Swarm Control via Tensorized Policy Coordination cs.LG updates on arXiv.org · 60d ago Boundary Variance Inflation Causes Acquisition Bias in Gaussian Processes cs.LG updates on arXiv.org · 60d ago Emergence via Phase Transitions: Mechanism Landscapes and Universal Convergence Across Complex Systems cs.LG updates on arXiv.org · 60d ago STARIXNet: Multivariate and Multi-attribute Deep Learning Approach to Real-Time Resource Allocation in Cloud Platforms cs.LG updates on arXiv.org · 60d ago TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation cs.LG updates on arXiv.org · 60d ago Enabling KV Caching of Shared Prefix for Diffusion Language Models cs.LG updates on arXiv.org · 60d ago When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery cs.LG updates on arXiv.org · 60d ago MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport cs.LG updates on arXiv.org · 60d ago Training-Inference Kernel Contracts: Bounding Divergence in Post-Training and Deployment cs.LG updates on arXiv.org · 60d ago Customer Churn Prediction on Structured Data Using FT-Transformer and Stacking Ensembles cs.LG updates on arXiv.org · 60d ago Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks cs.LG updates on arXiv.org · 60d ago From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUs cs.LG updates on arXiv.org · 60d ago The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers cs.LG updates on arXiv.org · 60d ago Optimality of Sequential Filtering Under Independent Cost and Selectivity Models cs.LG updates on arXiv.org · 60d ago ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research cs.LG updates on arXiv.org · 60d ago UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning cs.LG updates on arXiv.org · 60d ago Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates cs.LG updates on arXiv.org · 60d ago Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them cs.LG updates on arXiv.org · 60d ago Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference stat.ML updates on arXiv.org · 60d ago Transfer learning for causal forest stat.ML updates on arXiv.org · 60d ago Identifiability and Estimation for Unlabeled Finite Mixtures under Marginal Independence stat.ML updates on arXiv.org · 60d ago Barycentric Projections of Optimal Transport Plans on Riemannian Manifolds stat.ML updates on arXiv.org · 60d ago Variational Proximal Policy Optimization stat.ML updates on arXiv.org · 60d ago Beyond Additivity: Causal Discovery in Location-Scale Noise Models with Hidden Variables stat.ML updates on arXiv.org · 60d ago Vector Space of Cycles stat.ML updates on arXiv.org · 60d ago MEC-Cox: Machine-Learning-Assisted Generalized Entropy Calibration for ATT Marginal Hazard-Ratio Estimation stat.ML updates on arXiv.org · 60d ago Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models stat.ML updates on arXiv.org · 60d ago LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry stat.ML updates on arXiv.org · 60d ago Improving the sharpness in neural network-based parametric post-processing of ensemble forecasts stat.ML updates on arXiv.org · 60d ago Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation stat.ML updates on arXiv.org · 60d ago Generalization in Nonlinear Least Squares via Learned Feature Geometry stat.ML updates on arXiv.org · 60d ago Estimate Collapsibility of Causal Effects in Completed Partial DAGs via Strong d-Convex Hulls stat.ML updates on arXiv.org · 60d ago Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees stat.ML updates on arXiv.org · 60d ago SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths stat.ML updates on arXiv.org · 60d ago Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting stat.ML updates on arXiv.org · 60d ago Boundary Variance Inflation Causes Acquisition Bias in Gaussian Processes stat.ML updates on arXiv.org · 60d ago Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connections stat.ML updates on arXiv.org · 60d ago MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport stat.ML updates on arXiv.org · 60d ago Real-world grounding in agentic AI Amazon Science homepage · 60d ago Bridging intent and execution in agentic systems Amazon Science homepage · 60d ago Measuring the impact of learning with AI in Sierra Leone and beyond Google DeepMind News · 60d ago Statement: Anthropic warns of AI self-improvement risks, considers a pause Future of Life Institute · 61d ago Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios cs.LG updates on arXiv.org · 61d ago FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models cs.LG updates on arXiv.org · 61d ago Multi-Scale Feature Attention Network for Polymer Classification using THz Dual-Comb Spectroscopy cs.LG updates on arXiv.org · 61d ago MacArena: Benchmarking Computer Use Agents on an Online macOS Environment cs.LG updates on arXiv.org · 61d ago WAV: Multi-Resolution Block Residual Routing for Deep Decoder-Only Transformers cs.LG updates on arXiv.org · 61d ago Are you sure? A Comprehensive and Comprehensible Survey of Uncertainty Quantification in Symbolic Regression cs.LG updates on arXiv.org · 61d ago Generative Models Erode Human Temporal Learning Through Market Selection cs.LG updates on arXiv.org · 61d ago Skip a Layer or Loop It? Learning Program-of-Layers in LLMs cs.LG updates on arXiv.org · 61d ago Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems cs.LG updates on arXiv.org · 61d ago Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory cs.LG updates on arXiv.org · 61d ago The Identity Trap in EEG Foundation Models: A Diagnostic Audit cs.LG updates on arXiv.org · 61d ago Capturing non-Markovian dynamics in non-equilibrium stochastic systems using flow matching cs.LG updates on arXiv.org · 61d ago Explainable Runtime Dependency Tracking for AI-RAN Conflict Monitoring cs.LG updates on arXiv.org · 61d ago Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning cs.LG updates on arXiv.org · 61d ago Spatiotemporal Imputation with Graph-Informed Flow Matching cs.LG updates on arXiv.org · 61d ago Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers cs.LG updates on arXiv.org · 61d ago The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search cs.LG updates on arXiv.org · 61d ago RECAP: Regression Evaluation for Continual Adaptation of Prompts cs.LG updates on arXiv.org · 61d ago ShallowBench: Benchmarking Generative Drug Design Models on Shallow-Pocket Targets cs.LG updates on arXiv.org · 61d ago MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detection cs.LG updates on arXiv.org · 61d ago Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks stat.ML updates on arXiv.org · 61d ago Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods stat.ML updates on arXiv.org · 61d ago Empirical Transfer Operators and Finite-Sample Change Detection for Noisy Expanding Interval Maps stat.ML updates on arXiv.org · 61d ago The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces stat.ML updates on arXiv.org · 61d ago Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments stat.ML updates on arXiv.org · 61d ago Deep Single-Index Fr\'echet Regression stat.ML updates on arXiv.org · 61d ago Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions stat.ML updates on arXiv.org · 61d ago Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems stat.ML updates on arXiv.org · 61d ago TorchKM: A GPU-Oriented Library for Kernel Learning and Model Selection stat.ML updates on arXiv.org · 61d ago The Sharp Phase Transition of Tyler's M-Estimator for Robust Subspace Recovery stat.ML updates on arXiv.org · 61d ago Constructing VAE Latent Spaces with Prescribed Topology stat.ML updates on arXiv.org · 61d ago Information-Theoretic Bounds for Sparse Covariance Estimation in the Vertical-Split Distributed Model stat.ML updates on arXiv.org · 61d ago Principal Component Analysis for Multivariate Extremes stat.ML updates on arXiv.org · 61d ago Theory of learning of high-dimensional controlled non-linear dynamical systems (I): models and methods stat.ML updates on arXiv.org · 61d ago Covariance Shrinkage via Stochastic Interpolation stat.ML updates on arXiv.org · 61d ago Online Pandora's Box for Contextual LLM Cascading stat.ML updates on arXiv.org · 61d ago Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting stat.ML updates on arXiv.org · 61d ago Network Recovery from Cascade Data: A Debiased Jacobian-Based Machine Learning Approach stat.ML updates on arXiv.org · 61d ago Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies stat.ML updates on arXiv.org · 61d ago Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication stat.ML updates on arXiv.org · 61d ago Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG The latest research from Google · 64d ago Central Description Length (CDL) Clustering Validation Index stat.ML updates on arXiv.org · 64d ago HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation stat.ML updates on arXiv.org · 64d ago Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic-Gradient Noise and Localizing Taming stat.ML updates on arXiv.org · 64d ago Harnessing Source Heterogeneity for Cluster-Structured Transfer Learning stat.ML updates on arXiv.org · 64d ago TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness stat.ML updates on arXiv.org · 64d ago Environment-Robust Representation Learning with Empirical Bayes stat.ML updates on arXiv.org · 64d ago Sparse Functional Singular Value Decomposition for Biclustering and Triclustering Longitudinal Data stat.ML updates on arXiv.org · 64d ago Conformal Risk-Averse Decision Making with Action Conditional Guarantee stat.ML updates on arXiv.org · 64d ago Finding Most Influential Sets stat.ML updates on arXiv.org · 64d ago EML-CD: Causal Mechanism Recovery via EML Symbolic Trees in Structure Learning stat.ML updates on arXiv.org · 64d ago Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples stat.ML updates on arXiv.org · 64d ago Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader stat.ML updates on arXiv.org · 64d ago Effective Dimensionality as an Operator Invariant for Physics-Preserving Constraint Adaptation in Physics-Informed Neural Networks stat.ML updates on arXiv.org · 64d ago Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors stat.ML updates on arXiv.org · 64d ago Anchor PCA stat.ML updates on arXiv.org · 64d ago Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applications stat.ML updates on arXiv.org · 64d ago Symmetric Divergence and Normalized Similarity: A Unified Topological Framework for Representation Analysis stat.ML updates on arXiv.org · 64d ago Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction stat.ML updates on arXiv.org · 64d ago Conformal Risk Sharing: Certified Cost Allocation with Participation Guarantees stat.ML updates on arXiv.org · 64d ago DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables stat.ML updates on arXiv.org · 64d ago Startup helps retailers track their products in real-time MIT News - Machine learning · 64d ago Towards passive heart health monitoring via smartphone camera The latest research from Google · 64d ago Early Detection of Alzheimer's Disease Using Explainable Machine Learning on Clinical Biomarkers: A Multi-Class Classification Study Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) Dataset cs.LG updates on arXiv.org · 65d ago Novel Aspects of IEEE SA P3109 Arithmetic Formats for Machine Learning cs.LG updates on arXiv.org · 65d ago Position: Deployed Reinforcement Learning should be Continual cs.LG updates on arXiv.org · 65d ago Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent cs.LG updates on arXiv.org · 65d ago Do Transformers Need Three Projections? Systematic Study of QKV Variants cs.LG updates on arXiv.org · 65d ago Inverse Critical Experiment Design via Gradient Optimization and a Multigroup Attention-Based Neural Network Architecture cs.LG updates on arXiv.org · 65d ago Self-Distilled Policy Gradient cs.LG updates on arXiv.org · 65d ago Bayes-Sufficient Representations in Supervised Learning cs.LG updates on arXiv.org · 65d ago Unlocking Feature Learning in Gated Delta Networks at Scale cs.LG updates on arXiv.org · 65d ago LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection cs.LG updates on arXiv.org · 65d ago RUBAS: Rubric-Based Reinforcement Learning for Agent Safety cs.LG updates on arXiv.org · 65d ago A Goal-Set Characterization of Task Composition in the Boolean Task Algebra cs.LG updates on arXiv.org · 65d ago Spectral Scaling Laws of Muon cs.LG updates on arXiv.org · 65d ago LLM Compression with Jointly Optimizing Architectural and Quantization choices cs.LG updates on arXiv.org · 65d ago TPA-AD: A Two-Stage Pseudo Anomaly-Guided Method for Bearing Time-Series Anomaly Detection cs.LG updates on arXiv.org · 65d ago Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting cs.LG updates on arXiv.org · 65d ago Large Language Models Hack Rewards, and Society cs.LG updates on arXiv.org · 65d ago Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials cs.LG updates on arXiv.org · 65d ago Building The Ph(ysical)AI Layer Of Machine Intelligence cs.LG updates on arXiv.org · 65d ago Variance Reduction for Heavy-Tailed Monetization Metrics in Ranking Experiments via Post-Stratification cs.LG updates on arXiv.org · 65d ago Counterfactual Explanations for Deep Two-Sample Testing stat.ML updates on arXiv.org · 65d ago Finite-Iteration Local Dynamics and Warm Starts for Alternating Power Iteration in Spiked Tensor PCA stat.ML updates on arXiv.org · 65d ago REGAIN: REconciliation GAIN-driven Auxiliary Direction Learning stat.ML updates on arXiv.org · 65d ago Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks stat.ML updates on arXiv.org · 65d ago Flatness and Generalization: Learning Multi-Index Models with Homogeneous Neural Networks stat.ML updates on arXiv.org · 65d ago ReSGA: A Large Tail Risk Model for Learning Value-at-Risk and Expected Shortfall stat.ML updates on arXiv.org · 65d ago Bayesian learning for the stochastic shortest path problem stat.ML updates on arXiv.org · 65d ago Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent stat.ML updates on arXiv.org · 65d ago TPA-AD: A Two-Stage Pseudo Anomaly-Guided Method for Bearing Time-Series Anomaly Detection stat.ML updates on arXiv.org · 65d ago Variance Reduction for Heavy-Tailed Monetization Metrics in Ranking Experiments via Post-Stratification stat.ML updates on arXiv.org · 65d ago Low-rank Distributional Matrix Completion stat.ML updates on arXiv.org · 65d ago Exact Unlearning in Reinforcement Learning stat.ML updates on arXiv.org · 65d ago Edge of Stability Selectively Shapes Learning Across the Data Distribution stat.ML updates on arXiv.org · 65d ago Offline-to-Online Learning in Linear Bandits stat.ML updates on arXiv.org · 65d ago Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries stat.ML updates on arXiv.org · 65d ago When Do Fewer Coordinates Suffice in DP-SGD? stat.ML updates on arXiv.org · 65d ago Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD stat.ML updates on arXiv.org · 65d ago The price of multi-group transductive learning stat.ML updates on arXiv.org · 65d ago When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks stat.ML updates on arXiv.org · 65d ago Global Sketch-Based Watermarking for Diffusion Language Models stat.ML updates on arXiv.org · 65d ago The next chapter in flood resilience: Open sourcing Google’s hydrology framework The latest research from Google · 65d ago Ground truth is a process, not a dataset Amazon Science homepage · 65d ago NVIDIA Research Unlocks Advanced Grasping, Smarter Autonomous Driving and Agent Training at Scale NVIDIA Research Archives | NVIDIA Blog · 65d ago NVIDIA Enables the Next Era Of Physical AI Research With Agent Skills For Autonomous Vehicles, Robotics And Vision AI NVIDIA Research Archives | NVIDIA Blog · 65d ago FLI President on the White House Executive Order Future of Life Institute · 66d ago Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning cs.LG updates on arXiv.org · 66d ago Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent cs.LG updates on arXiv.org · 66d ago Making Brain-Computer Interfaces More Secure cs.LG updates on arXiv.org · 66d ago Assessing Region-Level EEG Contributions to Cognitive Workload Prediction cs.LG updates on arXiv.org · 66d ago Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection cs.LG updates on arXiv.org · 66d ago Graph Mamba Survival Analysis Based on Topology-Aware ordering cs.LG updates on arXiv.org · 66d ago Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation cs.LG updates on arXiv.org · 66d ago Cross-Modal Contrastive Learning of ECG and Angiography Representations for Severe Stenosis Classification cs.LG updates on arXiv.org · 66d ago ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services cs.LG updates on arXiv.org · 66d ago Geometry-Aware Tabular Diffusion cs.LG updates on arXiv.org · 66d ago Pruning Deep Neural Networks via the Marchenko--Pastur Distribution cs.LG updates on arXiv.org · 66d ago Building Better Activation Oracles cs.LG updates on arXiv.org · 66d ago Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs cs.LG updates on arXiv.org · 66d ago Regime-Arrival Uncertainty in Generalization Bounds under Distribution Shift cs.LG updates on arXiv.org · 66d ago CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning cs.LG updates on arXiv.org · 66d ago Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning cs.LG updates on arXiv.org · 66d ago AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret cs.LG updates on arXiv.org · 66d ago Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate cs.LG updates on arXiv.org · 66d ago Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis cs.LG updates on arXiv.org · 66d ago Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals cs.LG updates on arXiv.org · 66d ago Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery stat.ML updates on arXiv.org · 66d ago Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics stat.ML updates on arXiv.org · 66d ago State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation stat.ML updates on arXiv.org · 66d ago ScoreStop: Gradient-based early stopping using functional score tests stat.ML updates on arXiv.org · 66d ago Scalable Derivative Gaussian Processes via Exact Gradient Reduction stat.ML updates on arXiv.org · 66d ago Trajectory-Aware Node Contributions and the Limits of Static Controllability stat.ML updates on arXiv.org · 66d ago An Asymptotic Theory of Chain-of-Thought in In-Context Learning stat.ML updates on arXiv.org · 66d ago Hierarchies of Calibration: Classification meets Regression stat.ML updates on arXiv.org · 66d ago Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification stat.ML updates on arXiv.org · 66d ago A Robust Optimization Approach to Sparse Principal Component Analysis stat.ML updates on arXiv.org · 66d ago Few-Shot Prediction for Pulsar Noise with Long Short-Term Memory Network stat.ML updates on arXiv.org · 66d ago Set-Preserving Calibration from Conformal P-Values to E-Values stat.ML updates on arXiv.org · 66d ago Resource-Constrained Adaptive Inference for Sequential Pricing stat.ML updates on arXiv.org · 66d ago A Quantitative Approximation Framework for Flow Distillation in Diffusion Models stat.ML updates on arXiv.org · 66d ago Privacy-Robust Incrementality Measurement for Advertising Systems under Signal Loss stat.ML updates on arXiv.org · 66d ago Rashomon-Seeded Annealing for Robust Bayesian Inference in Factorial Designs stat.ML updates on arXiv.org · 66d ago Recovering Direct Price Effects of Environmental Amenities in Housing Markets: Regression and Causal Machine Learning Model Assessment with Empirical Monte Carlo Simulation stat.ML updates on arXiv.org · 66d ago Neural Posterior Estimation for Stochastic Epidemic Models Using Final Outcome Data stat.ML updates on arXiv.org · 66d ago Neural Networks Provably Learn Spectral Representations for Group Composition stat.ML updates on arXiv.org · 66d ago A Fast Screening Approach for High-dimensional Outcomes and High-dimensional Predictors stat.ML updates on arXiv.org · 66d ago BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization cs.LG updates on arXiv.org · 67d ago DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions cs.LG updates on arXiv.org · 67d ago Hoeffding Concept Bottleneck Models with Applications to Overhead Images cs.LG updates on arXiv.org · 67d ago From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models cs.LG updates on arXiv.org · 67d ago A Shared Valence Axis Across Modern LLMs and Human EEG: The Saturation Regularity cs.LG updates on arXiv.org · 67d ago Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks cs.LG updates on arXiv.org · 67d ago Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization cs.LG updates on arXiv.org · 67d ago World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications cs.LG updates on arXiv.org · 67d ago On Effectiveness and Efficiency of Agentic Tool-calling and RL Training cs.LG updates on arXiv.org · 67d ago Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey cs.LG updates on arXiv.org · 67d ago Geometric Erasure by Contrastive Velocity Matching in Rectified Flows cs.LG updates on arXiv.org · 67d ago Adaptive data selection improves wearable prediction under low baseline performance cs.LG updates on arXiv.org · 67d ago BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding cs.LG updates on arXiv.org · 67d ago RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting cs.LG updates on arXiv.org · 67d ago Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying cs.LG updates on arXiv.org · 67d ago ChurnNet: A Optimized Modern AI for Churn Prediction cs.LG updates on arXiv.org · 67d ago Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection cs.LG updates on arXiv.org · 67d ago Agentic Transformers Provably Learn to Search via Reinforcement Learning cs.LG updates on arXiv.org · 67d ago AI-Guided Design and Optimization of Graphite-Based Anodes via Iterative Experimental Feedback cs.LG updates on arXiv.org · 67d ago Learning to Construct Practical Agentic Systems cs.LG updates on arXiv.org · 67d ago Interpreting FCDNNs via RG on Exponential Family stat.ML updates on arXiv.org · 67d ago Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach stat.ML updates on arXiv.org · 67d ago Is Zero-Shot Super-Resolution Possible in Operator Learning? stat.ML updates on arXiv.org · 67d ago ERICA: Quantifying Replicability of Cluster Analysis stat.ML updates on arXiv.org · 67d ago Riemannian Stochastic Optimization for Sufficient Dimension Reduction stat.ML updates on arXiv.org · 67d ago Parameter-Free and Group Conditional Online Conformal Prediction stat.ML updates on arXiv.org · 67d ago Spectra-Guided Neural Tucker Factorization stat.ML updates on arXiv.org · 67d ago Taming the Loss Landscape of PINNs with Noisy Feynman-Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds stat.ML updates on arXiv.org · 67d ago On Median of Incomplete U-Statistics stat.ML updates on arXiv.org · 67d ago Statistical Testing on Directed Graphs by Surrogate Data Generation stat.ML updates on arXiv.org · 67d ago Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifiers stat.ML updates on arXiv.org · 67d ago Bandit Simulation for Average Reward Inference stat.ML updates on arXiv.org · 67d ago Efficient Synthetic Network Generation via Latent Embedding Reconstruction stat.ML updates on arXiv.org · 67d ago Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates stat.ML updates on arXiv.org · 67d ago Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces stat.ML updates on arXiv.org · 67d ago Distribution-free changepoint localization after sequential change detection stat.ML updates on arXiv.org · 67d ago On the Uncertainty Quantification Ability of Tabular Foundation Models stat.ML updates on arXiv.org · 67d ago Computation-Aware Kalman Filtering with Model Selection for Neural Dynamics stat.ML updates on arXiv.org · 67d ago Self-Regulating Annealing in Heavy-Tailed Diffusion Models stat.ML updates on arXiv.org · 67d ago Provable Data Scaling Law for Meta Learning via Complexity Minimization stat.ML updates on arXiv.org · 67d ago QASM-Eval: A Dataset to Train and Evaluate LLMs on OpenQASM-3 Beyond Quantum Circuits cs.LG updates on arXiv.org · 68d ago Gait2Hip-60: A Unified Deep Learning Benchmark for Predicting Hip Muscle Forces and Joint Moments from Multi-Cadence Gait Kinematics cs.LG updates on arXiv.org · 68d ago Unicorn: Scaling High-Dimensional Time Series Forecasting via Universal Correlation Modeling cs.LG updates on arXiv.org · 68d ago When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception cs.LG updates on arXiv.org · 68d ago LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study cs.LG updates on arXiv.org · 68d ago Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification cs.LG updates on arXiv.org · 68d ago A Novel Evaluation Metric for Unsupervised Learning in AIS-Based Maritime Anomaly Detection: MADQI cs.LG updates on arXiv.org · 68d ago NumLeak: Public Numeric Benchmarks as Latent Labels in Foundation Models cs.LG updates on arXiv.org · 68d ago LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis cs.LG updates on arXiv.org · 68d ago Calibrated Preference Learning: The Case of Label Ranking cs.LG updates on arXiv.org · 68d ago Bounded Behavioral Indistinguishability for Black-Box LLM Distillation cs.LG updates on arXiv.org · 68d ago VeriGate: Verifier-Gated Step-Level Supervision for GRPO cs.LG updates on arXiv.org · 68d ago A Unified Framework for Gradient Aggregation in Multi-Objective Optimization cs.LG updates on arXiv.org · 68d ago DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers cs.LG updates on arXiv.org · 68d ago Scalable Constrained Multi-Agent Reinforcement Learning via State Augmentation and Consensus for Separable Dynamics cs.LG updates on arXiv.org · 68d ago idSCD: Identifying Training Datasets through Semantic Correlation Descriptors cs.LG updates on arXiv.org · 68d ago Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks? cs.LG updates on arXiv.org · 68d ago Universal Multiclass Transductive Online Learning cs.LG updates on arXiv.org · 68d ago Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability cs.LG updates on arXiv.org · 68d ago Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting cs.LG updates on arXiv.org · 68d ago Improved Distribution Estimation in $\ell_\infty$ stat.ML updates on arXiv.org · 68d ago Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles stat.ML updates on arXiv.org · 68d ago Is the Last Layer Sufficient for Uncertainty Quantification? stat.ML updates on arXiv.org · 68d ago Batched Stochastic Linear Bandits with 1-Bit Communication Constraints stat.ML updates on arXiv.org · 68d ago Hedging on the Frontier: Learning New Tasks with Few Samples stat.ML updates on arXiv.org · 68d ago Routing on the Stiefel Manifold: When Does Adaptive Subspace Selection Help for Cross-Domain EEG Decoding? stat.ML updates on arXiv.org · 68d ago Free energy Estimation on Any State Space stat.ML updates on arXiv.org · 68d ago Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks stat.ML updates on arXiv.org · 68d ago Memory by Design: Probabilistic Sequence Layers stat.ML updates on arXiv.org · 68d ago Correcting Split Selection in Online Decision Trees via Anytime-Valid Inference stat.ML updates on arXiv.org · 68d ago Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift stat.ML updates on arXiv.org · 68d ago Log-Ratio Propagation on the Simplex: A Theory of Cellwise Contamination for Compositional Data stat.ML updates on arXiv.org · 68d ago Calibrated Preference Learning: The Case of Label Ranking stat.ML updates on arXiv.org · 68d ago Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics stat.ML updates on arXiv.org · 68d ago Benchmark of Likelihood-Free Inference Methods based on Neural and Optimal Transport Approaches stat.ML updates on arXiv.org · 68d ago True Self-Avoiding Walk for Accelerating Markov-Chain Monte Carlo Integration stat.ML updates on arXiv.org · 68d ago Active Timepoint Selection for Learning Measure-Valued Trajectories stat.ML updates on arXiv.org · 68d ago SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs stat.ML updates on arXiv.org · 68d ago Moment-Based Inference for Regression with Latent Dirichlet Covariates stat.ML updates on arXiv.org · 68d ago Kalimati Vegetable Price Index Forecasting with a Momentum Corrected Online Stacking Ensemble stat.ML updates on arXiv.org · 68d ago One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them cs.LG updates on arXiv.org · 71d ago Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents cs.LG updates on arXiv.org · 71d ago Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT? cs.LG updates on arXiv.org · 71d ago Molecular Lead Optimization via Agentic Tool Planning cs.LG updates on arXiv.org · 71d ago Self-Play Reinforcement Learning under Imperfect Information in Big 2 cs.LG updates on arXiv.org · 71d ago Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision cs.LG updates on arXiv.org · 71d ago Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models cs.LG updates on arXiv.org · 71d ago PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation cs.LG updates on arXiv.org · 71d ago TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models cs.LG updates on arXiv.org · 71d ago Balancing Multimodal Learning through Label Space Reshaping cs.LG updates on arXiv.org · 71d ago Representation Alignment Rests on Linear Structure cs.LG updates on arXiv.org · 71d ago Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit cs.LG updates on arXiv.org · 71d ago Towards Continuous-time Causal Foundation Models cs.LG updates on arXiv.org · 71d ago Context Distillation as Latent Memory Management cs.LG updates on arXiv.org · 71d ago Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models cs.LG updates on arXiv.org · 71d ago Spectral Guidance for Flexible and Efficient Control of Diffusion Models cs.LG updates on arXiv.org · 71d ago Sequential Physics-Constrained Neural Operator Forward Modeling for the $\textit{Norne}$ Reservoir System cs.LG updates on arXiv.org · 71d ago Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems cs.LG updates on arXiv.org · 71d ago When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL cs.LG updates on arXiv.org · 71d ago CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models cs.LG updates on arXiv.org · 71d ago Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions stat.ML updates on arXiv.org · 71d ago Anytime-Valid Federated Conformal RAG for LLM Swarms stat.ML updates on arXiv.org · 71d ago Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research stat.ML updates on arXiv.org · 71d ago Deep Optimal Individualized Treatment Rules for Bivariate Survival Outcomes via Adaptive Prediction-Powered Learning stat.ML updates on arXiv.org · 71d ago Matching Rates and Optimal Allocation for Federated Probe-Logit Distillation under Heterogeneous Bandwidth Budgets stat.ML updates on arXiv.org · 71d ago Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data stat.ML updates on arXiv.org · 71d ago Instance-dependent Stochastic Lipschitz bandit stat.ML updates on arXiv.org · 71d ago Joint Model and Data Sparsification via the Marginal Likelihood stat.ML updates on arXiv.org · 71d ago Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions stat.ML updates on arXiv.org · 71d ago Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks stat.ML updates on arXiv.org · 71d ago Wasserstein Contraction of Coordinate Ascent Variational Inference stat.ML updates on arXiv.org · 71d ago Leave a Window Out: Modifying the Jackknife for Predictive Inference in Time Series stat.ML updates on arXiv.org · 71d ago Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion stat.ML updates on arXiv.org · 71d ago Saddle Networks: Structure-Preserving Architectures for Convex-Concave Functions stat.ML updates on arXiv.org · 71d ago Conf-Gen: Conformal Uncertainty Quantification for Generative Models stat.ML updates on arXiv.org · 71d ago Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning stat.ML updates on arXiv.org · 71d ago Optimal Gap-Dependent Regret for Private Stochastic Decision-Theoretic Online Learning stat.ML updates on arXiv.org · 71d ago Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias stat.ML updates on arXiv.org · 71d ago Bayesian Multiplicity Correction in the Probabilistic Forward Stepwise Framework stat.ML updates on arXiv.org · 71d ago Causal Label Recovery in Payment Networks stat.ML updates on arXiv.org · 71d ago A New Era of Discovery: Google Research at I/O 2026 The latest research from Google · 71d ago NVIDIA Research Advances Robotics From Simulation to the Real World NVIDIA Research Archives | NVIDIA Blog · 71d ago How flat is replacing fat in AWS data center networks Amazon Science homepage · 72d ago Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity cs.LG updates on arXiv.org · 72d ago IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation cs.LG updates on arXiv.org · 72d ago A Simple State Space Model Excels at Multivariate Time Series Classification cs.LG updates on arXiv.org · 72d ago $E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference cs.LG updates on arXiv.org · 72d ago Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey cs.LG updates on arXiv.org · 72d ago Metric-Aware PCA as a Linear Instance of Geometric Deep Learning cs.LG updates on arXiv.org · 72d ago Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility cs.LG updates on arXiv.org · 72d ago Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift cs.LG updates on arXiv.org · 72d ago Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection cs.LG updates on arXiv.org · 72d ago HEAL: Resilient and Self-* Hub-based Learning cs.LG updates on arXiv.org · 72d ago Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective cs.LG updates on arXiv.org · 72d ago Resource-Constrained Affect Modelling via Variance Regularisation Pruning cs.LG updates on arXiv.org · 72d ago Energy-Structured Low-Rank Adaptation for Continual Learning cs.LG updates on arXiv.org · 72d ago Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation cs.LG updates on arXiv.org · 72d ago GenSBI: Generative Methods for Simulation-Based Inference in JAX cs.LG updates on arXiv.org · 72d ago SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training cs.LG updates on arXiv.org · 72d ago The Fundamental Limits of Fraud Detection in Card Payment Networks cs.LG updates on arXiv.org · 72d ago Information-theoretic Multimodal Representation Learning for Electrocardiogram Signals cs.LG updates on arXiv.org · 72d ago Gradient Transformer: Learning to Generate Updates for LLMs cs.LG updates on arXiv.org · 72d ago The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution cs.LG updates on arXiv.org · 72d ago Calibrated Inference for the Conditional Average Treatment Effect in the Few-Placebo Regime via Gaussian Processes stat.ML updates on arXiv.org · 72d ago Stop Suppressing the Tail: Causal Inference for Extreme Events stat.ML updates on arXiv.org · 72d ago Iterative Causal Discovery: Per-Edge Impossibility Certificates, Tier-Aware Oracle Queries, and the $1+K$ Lower Bound stat.ML updates on arXiv.org · 72d ago Triangular-Reference Schr\"odinger Bridges for Time Series Generation stat.ML updates on arXiv.org · 72d ago Identifiable Bayesian Deep Generative Copulas with Unknown Layer Widths for Data with Arbitrary Marginal Distributions stat.ML updates on arXiv.org · 72d ago Semiparametrically Efficient Inference for Kernel Measures of Noise Heterogeneity stat.ML updates on arXiv.org · 72d ago Accelerating Reinforcement Learning Training Using Simulation Surrogate Models stat.ML updates on arXiv.org · 72d ago Evolving and Detecting Multi-Turn Deception using Geometric Signatures stat.ML updates on arXiv.org · 72d ago Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning stat.ML updates on arXiv.org · 72d ago Soft Specialists: $\alpha$-R\'enyi Ensembles for Uncertainty-Aware LLM Post-Training stat.ML updates on arXiv.org · 72d ago Learning to target with network interference stat.ML updates on arXiv.org · 72d ago Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency stat.ML updates on arXiv.org · 72d ago Deep Neural Network Training as Random Effects: An Optimization-Inference Duality stat.ML updates on arXiv.org · 72d ago The conditional-mean barrier: From deterministic regression to conditional distribution learning stat.ML updates on arXiv.org · 72d ago Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings stat.ML updates on arXiv.org · 72d ago Counterfactually Fair Regression via Optimal Transport stat.ML updates on arXiv.org · 72d ago Insurance Pricing Optimization via Off-Policy Evaluation stat.ML updates on arXiv.org · 72d ago Decision-focused learning for optimal PV-Battery scheduling stat.ML updates on arXiv.org · 72d ago Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation stat.ML updates on arXiv.org · 72d ago Bridging Maximum Likelihood and Optimal Transport for Efficient Inference and Model Selection in Stochastic Block Models stat.ML updates on arXiv.org · 72d ago Amazon Research Awards recipients announced Amazon Science homepage · 72d ago Private analytics via zero-trust aggregation The latest research from Google · 72d ago GEM: Geometric Entropy Mixing for Optimal LLM Data Curation cs.LG updates on arXiv.org · 73d ago The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models cs.LG updates on arXiv.org · 73d ago AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion cs.LG updates on arXiv.org · 73d ago SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection cs.LG updates on arXiv.org · 73d ago Neural Bayesian Sequential Routing cs.LG updates on arXiv.org · 73d ago TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models cs.LG updates on arXiv.org · 73d ago On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach cs.LG updates on arXiv.org · 73d ago Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning cs.LG updates on arXiv.org · 73d ago When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection cs.LG updates on arXiv.org · 73d ago ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling cs.LG updates on arXiv.org · 73d ago InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization cs.LG updates on arXiv.org · 73d ago GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training cs.LG updates on arXiv.org · 73d ago Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training cs.LG updates on arXiv.org · 73d ago HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals cs.LG updates on arXiv.org · 73d ago Modeling Dynamic Mixtures of Time-Delay Systems from Streaming Time Series cs.LG updates on arXiv.org · 73d ago Co-folding model guided by structural proteomics cs.LG updates on arXiv.org · 73d ago Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection cs.LG updates on arXiv.org · 73d ago On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series cs.LG updates on arXiv.org · 73d ago From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD cs.LG updates on arXiv.org · 73d ago Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks cs.LG updates on arXiv.org · 73d ago Learning Nonlinear Factor Models with Unknown Monotone Links from Incomplete and Noisy Data stat.ML updates on arXiv.org · 73d ago Beyond Differences: Doubly Robust Meta-Learners for Ratio-Based Treatment Effects stat.ML updates on arXiv.org · 73d ago When Does LeJEPA Learn a World Model? stat.ML updates on arXiv.org · 73d ago CART Random Forests as Sequential Allocation over Random Opportunity Sets: A Stochastic-Control Theory of Ensemble Risk stat.ML updates on arXiv.org · 73d ago Transformers Can Learn Posterior Predictive Distributions In-Context stat.ML updates on arXiv.org · 73d ago Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks stat.ML updates on arXiv.org · 73d ago Constrained Bayesian Experimental Design via Online Planning stat.ML updates on arXiv.org · 73d ago Causal Representation Learning for Generalisable Recommendation stat.ML updates on arXiv.org · 73d ago Gaussian Process-based learning with new MCMC-based implementation of Wishart prior on correlation matrix stat.ML updates on arXiv.org · 73d ago Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models stat.ML updates on arXiv.org · 73d ago From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD stat.ML updates on arXiv.org · 73d ago A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning stat.ML updates on arXiv.org · 73d ago Fast Convergence of Policy Regret in Learning Stochastic Optimal Control stat.ML updates on arXiv.org · 73d ago Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback stat.ML updates on arXiv.org · 73d ago Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking stat.ML updates on arXiv.org · 73d ago Function-Valued Causal Influence in Nonlinear Time Series stat.ML updates on arXiv.org · 73d ago Confounder Detection via Treatment Intent: A New Observational Study Design stat.ML updates on arXiv.org · 73d ago Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing stat.ML updates on arXiv.org · 73d ago Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift stat.ML updates on arXiv.org · 73d ago Sample Complexity of Policy Gradient for Log-Growth Control stat.ML updates on arXiv.org · 73d ago Diverse reasoning traces teach LLMs to make better decisions Amazon Science homepage · 73d ago Algometrics: Forecasting Under Algorithmic Feedback cs.LG updates on arXiv.org · 74d ago Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection cs.LG updates on arXiv.org · 74d ago CAFD: Concept-Aware DNN Fault Detection using VLMs cs.LG updates on arXiv.org · 74d ago Towards Verifiable Transformers: Solver-Checkable Circuit Explanations cs.LG updates on arXiv.org · 74d ago Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation cs.LG updates on arXiv.org · 74d ago Hidden-State Privacy Has an Empty Middle cs.LG updates on arXiv.org · 74d ago LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs cs.LG updates on arXiv.org · 74d ago A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood? cs.LG updates on arXiv.org · 74d ago Mixture of Complementary Agents for Robust LLM Ensemble cs.LG updates on arXiv.org · 74d ago Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing cs.LG updates on arXiv.org · 74d ago Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions cs.LG updates on arXiv.org · 74d ago Feature Lottery? A Bifurcation Theory of Concept Emergence cs.LG updates on arXiv.org · 74d ago Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning cs.LG updates on arXiv.org · 74d ago Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers cs.LG updates on arXiv.org · 74d ago Federated Learning over Human-Body Communication for On-Body Edge Intelligence: A Survey, Taxonomy, and BODYFED-HBC Scheduling Vignette cs.LG updates on arXiv.org · 74d ago Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion cs.LG updates on arXiv.org · 74d ago Not All Transitions Matter: Evidence from PPO cs.LG updates on arXiv.org · 74d ago Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks cs.LG updates on arXiv.org · 74d ago Overcoming "Physics Shock" in Earth Observation A Heteroscedastic Uncertainty Framework for PINN-based Flood Inference cs.LG updates on arXiv.org · 74d ago Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions cs.LG updates on arXiv.org · 74d ago Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs stat.ML updates on arXiv.org · 74d ago Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines stat.ML updates on arXiv.org · 74d ago Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination stat.ML updates on arXiv.org · 74d ago MEDAL: Manifold Embedding Distillation via Autoencoder Learning stat.ML updates on arXiv.org · 74d ago Multicalibration Boosting: Theory, Convergence, and Transferability stat.ML updates on arXiv.org · 74d ago Clustering based on Stochastic Dominance with application for risk averters and risk seekers stat.ML updates on arXiv.org · 74d ago Affinity Graph Connectivity in Convex Clustering stat.ML updates on arXiv.org · 74d ago How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis stat.ML updates on arXiv.org · 74d ago Estimating Mixture Distributions via Stochastic Mirror Descent stat.ML updates on arXiv.org · 74d ago Counterfactually Safe Reinforcement Learning stat.ML updates on arXiv.org · 74d ago Nystr\"om Kernel Stein Discrepancy Tests stat.ML updates on arXiv.org · 74d ago Choosing Online Experiment Designs under Interference in Ads, Recommendations, and Member-Experience Systems stat.ML updates on arXiv.org · 74d ago Learning manifold diffusion semigroups from graph transition matrices stat.ML updates on arXiv.org · 74d ago Mean-Shift PCA by Knockoff Mean stat.ML updates on arXiv.org · 74d ago Guided Flow Matching for Forward and Inverse PDE Problems with Sparse Observations: Algorithm and Theory stat.ML updates on arXiv.org · 74d ago From DPPs to $k$-DPPs: identifiability analysis via spectral decomposition stat.ML updates on arXiv.org · 74d ago Rao-Blackwellized Score Matching on Manifolds stat.ML updates on arXiv.org · 74d ago Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent stat.ML updates on arXiv.org · 74d ago Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification stat.ML updates on arXiv.org · 74d ago Learning Sparse Compositional Functions with Norm-Constrained Neural Networks stat.ML updates on arXiv.org · 74d ago Latent Cache Flow: Model-to-Model Communication Without Text cs.LG updates on arXiv.org · 75d ago Reading Calibrated Uncertainty from Language Model Trajectories cs.LG updates on arXiv.org · 75d ago FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence cs.LG updates on arXiv.org · 75d ago FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning cs.LG updates on arXiv.org · 75d ago The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models cs.LG updates on arXiv.org · 75d ago Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity cs.LG updates on arXiv.org · 75d ago MedExpMem: Adapting Experience Memory for Differential Diagnosis cs.LG updates on arXiv.org · 75d ago When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions cs.LG updates on arXiv.org · 75d ago WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems cs.LG updates on arXiv.org · 75d ago Tensor Cache: Eviction-conditioned Associative Memory for Transformers cs.LG updates on arXiv.org · 75d ago Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems cs.LG updates on arXiv.org · 75d ago From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data cs.LG updates on arXiv.org · 75d ago FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning cs.LG updates on arXiv.org · 75d ago Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models cs.LG updates on arXiv.org · 75d ago Building a privacy-preserving Federated Recommender system for mobile devices cs.LG updates on arXiv.org · 75d ago Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning cs.LG updates on arXiv.org · 75d ago MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination cs.LG updates on arXiv.org · 75d ago FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data cs.LG updates on arXiv.org · 75d ago Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization cs.LG updates on arXiv.org · 75d ago Learned Relay Representations for Forward-Thinking Discrete Diffusion Models cs.LG updates on arXiv.org · 75d ago Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation stat.ML updates on arXiv.org · 75d ago KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis stat.ML updates on arXiv.org · 75d ago LLM Sparsity Prior for Robust Feature Selection stat.ML updates on arXiv.org · 75d ago Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models stat.ML updates on arXiv.org · 75d ago Coupled Training with Privileged Information and Unlabeled Data stat.ML updates on arXiv.org · 75d ago Concomitant DAG Learning: On the Roles of Noise Adaptivity, Sparsity, and Non-negativity stat.ML updates on arXiv.org · 75d ago Asymmetric Scaling Laws from Sparse Features stat.ML updates on arXiv.org · 75d ago Dirichlet-Based Monte Carlo Dropout for Uncertainty Estimation in Neural Networks stat.ML updates on arXiv.org · 75d ago Learning Kernel-Based MDPs from Episodic Preferential Feedback stat.ML updates on arXiv.org · 75d ago Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer stat.ML updates on arXiv.org · 75d ago On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy stat.ML updates on arXiv.org · 75d ago Symbolic Density Estimation for Discrete Distributions stat.ML updates on arXiv.org · 75d ago Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation stat.ML updates on arXiv.org · 75d ago Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity stat.ML updates on arXiv.org · 75d ago Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning stat.ML updates on arXiv.org · 75d ago Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics stat.ML updates on arXiv.org · 75d ago HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation stat.ML updates on arXiv.org · 75d ago Anytime Training with Schedule-Free Spectral Optimization stat.ML updates on arXiv.org · 75d ago Mode-Shape Expansion Using Physics-Constrained Gaussian Process Regression stat.ML updates on arXiv.org · 75d ago Robust OT-Guided Generative Residual Domain Adaptation for Bike-Sharing Demand Prediction under Temporal Domain Shift stat.ML updates on arXiv.org · 75d ago Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding cs.LG updates on arXiv.org · 77d ago Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation cs.LG updates on arXiv.org · 77d ago The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity cs.LG updates on arXiv.org · 77d ago Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins cs.LG updates on arXiv.org · 77d ago Double descent for least-squares interpolation on contaminated data: A simulation study cs.LG updates on arXiv.org · 77d ago HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine cs.LG updates on arXiv.org · 77d ago Predicting Performance of Symbolic and Prompt Programs with Examples cs.LG updates on arXiv.org · 77d ago Harnesses for Inference-Time Alignment over Execution Trajectories cs.LG updates on arXiv.org · 77d ago A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction cs.LG updates on arXiv.org · 77d ago DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models cs.LG updates on arXiv.org · 77d ago Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series cs.LG updates on arXiv.org · 77d ago Provable Joint Decontamination for Benchmarking Multiple Large Language Models cs.LG updates on arXiv.org · 77d ago Tabular foundation models for robust calibration of near-infrared chemical sensing data cs.LG updates on arXiv.org · 77d ago PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting cs.LG updates on arXiv.org · 77d ago Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift cs.LG updates on arXiv.org · 77d ago TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems cs.LG updates on arXiv.org · 77d ago Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising cs.LG updates on arXiv.org · 77d ago From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment cs.LG updates on arXiv.org · 77d ago AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems cs.LG updates on arXiv.org · 77d ago Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection cs.LG updates on arXiv.org · 77d ago Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks stat.ML updates on arXiv.org · 78d ago Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions stat.ML updates on arXiv.org · 78d ago Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling stat.ML updates on arXiv.org · 78d ago Support-aware offline policy selection for advertising marketplaces stat.ML updates on arXiv.org · 78d ago Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks stat.ML updates on arXiv.org · 78d ago From Betting to Empirical Bernstein LIL stat.ML updates on arXiv.org · 78d ago Departure from Regularity: Degree Heterogeneity and Eigengap as the Structural Drivers of ASE-LSE Latent Subspace Disagreement stat.ML updates on arXiv.org · 78d ago Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions stat.ML updates on arXiv.org · 78d ago A Martingale Kernel Independence Test stat.ML updates on arXiv.org · 78d ago Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models stat.ML updates on arXiv.org · 78d ago Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data stat.ML updates on arXiv.org · 78d ago The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity stat.ML updates on arXiv.org · 78d ago Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery stat.ML updates on arXiv.org · 78d ago Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs stat.ML updates on arXiv.org · 78d ago Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift stat.ML updates on arXiv.org · 78d ago Distribution-free root cause analysis stat.ML updates on arXiv.org · 78d ago Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos stat.ML updates on arXiv.org · 78d ago Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective stat.ML updates on arXiv.org · 78d ago On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents stat.ML updates on arXiv.org · 78d ago MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation stat.ML updates on arXiv.org · 78d ago Building accessibility tools on a truly open foundation Ai2 Blog · 79d ago Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models cs.LG updates on arXiv.org · 79d ago GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation cs.LG updates on arXiv.org · 79d ago TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data cs.LG updates on arXiv.org · 79d ago Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine cs.LG updates on arXiv.org · 79d ago MagBridge-Battery: A Synthetic Bridge Dataset for Li-ion Magnetometry and State-of-Health Diagnostics cs.LG updates on arXiv.org · 79d ago Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry cs.LG updates on arXiv.org · 79d ago LEAP: A closed-loop framework for perovskite precursor additive discovery cs.LG updates on arXiv.org · 79d ago GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents cs.LG updates on arXiv.org · 79d ago CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning cs.LG updates on arXiv.org · 79d ago Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification cs.LG updates on arXiv.org · 79d ago Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization cs.LG updates on arXiv.org · 79d ago Physics-informed convolutional neural networks for fluid flow through porous media cs.LG updates on arXiv.org · 79d ago Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty cs.LG updates on arXiv.org · 79d ago FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning cs.LG updates on arXiv.org · 79d ago Instance Discrimination for Link Prediction cs.LG updates on arXiv.org · 79d ago It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs cs.LG updates on arXiv.org · 79d ago Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing cs.LG updates on arXiv.org · 79d ago Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding cs.LG updates on arXiv.org · 79d ago Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity cs.LG updates on arXiv.org · 79d ago Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs cs.LG updates on arXiv.org · 79d ago Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity stat.ML updates on arXiv.org · 79d ago Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models stat.ML updates on arXiv.org · 79d ago Contradiction Graphs Determine VC Dimension stat.ML updates on arXiv.org · 79d ago Sample Complexity of Transfer Learning: An Optimal Transport Approach stat.ML updates on arXiv.org · 79d ago Spectral bandits for smooth graph functions with applications in recommender systems stat.ML updates on arXiv.org · 79d ago Group-Aware Matrix Estimation and Latent Subspace Recovery stat.ML updates on arXiv.org · 79d ago Conditioning Gaussian Processes on Almost Anything stat.ML updates on arXiv.org · 79d ago A Rigorous, Tractable Measure of Model Complexity stat.ML updates on arXiv.org · 79d ago Federated LoRA Fine-Tuning for LLMs via Collaborative Alignment stat.ML updates on arXiv.org · 79d ago Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference stat.ML updates on arXiv.org · 79d ago Large-Step Training Dynamics of a Two-Factor Linear Transformer Model stat.ML updates on arXiv.org · 79d ago Semiparametric Efficient Bilevel Gradient Estimation stat.ML updates on arXiv.org · 79d ago Memorisation, convergence and generalisation in generative models stat.ML updates on arXiv.org · 79d ago A Differentiable Measure of Algebraic Complexity: Provably Exact Discovery of Group Structures stat.ML updates on arXiv.org · 79d ago Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity stat.ML updates on arXiv.org · 79d ago Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs stat.ML updates on arXiv.org · 79d ago Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels stat.ML updates on arXiv.org · 79d ago Score-Based Causal Discovery of Latent Variable Causal Models stat.ML updates on arXiv.org · 79d ago Understanding Deterioration Random Effects for Causal Discovery in Infrastructure Management stat.ML updates on arXiv.org · 79d ago CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support stat.ML updates on arXiv.org · 79d ago Magnificent Humanity – The Pope’s First Encyclical Concerns AI Future of Life Institute · 79d ago Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance cs.LG updates on arXiv.org · 80d ago Robust Basis Spline Decoupling for the Compression of Transformer Models cs.LG updates on arXiv.org · 80d ago HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models cs.LG updates on arXiv.org · 80d ago UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing cs.LG updates on arXiv.org · 80d ago Simply Stabilizing the Loop via Fully Looped Transformer cs.LG updates on arXiv.org · 80d ago Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis cs.LG updates on arXiv.org · 80d ago ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning cs.LG updates on arXiv.org · 80d ago Theory-optimal Quantization Based on Flatness cs.LG updates on arXiv.org · 80d ago PROWL: Prioritized Regret-Driven Optimization for World Model Learning cs.LG updates on arXiv.org · 80d ago Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning cs.LG updates on arXiv.org · 80d ago Block-Based Double Decoders cs.LG updates on arXiv.org · 80d ago Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect cs.LG updates on arXiv.org · 80d ago Metric-Gradient Projection for Stable Multi-Agent Policy Learning cs.LG updates on arXiv.org · 80d ago D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting cs.LG updates on arXiv.org · 80d ago PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines cs.LG updates on arXiv.org · 80d ago Composition of Memory Experts for Diffusion World Models cs.LG updates on arXiv.org · 80d ago How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines cs.LG updates on arXiv.org · 80d ago DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training cs.LG updates on arXiv.org · 80d ago Symmetry in the Wild: The Role of Equivariance in Neural Fluid Surrogates cs.LG updates on arXiv.org · 80d ago Multi-Token Residual Prediction cs.LG updates on arXiv.org · 80d ago Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors stat.ML updates on arXiv.org · 80d ago Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models stat.ML updates on arXiv.org · 80d ago Conformal Prediction via Transported Beta Laws stat.ML updates on arXiv.org · 80d ago Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming stat.ML updates on arXiv.org · 80d ago Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection stat.ML updates on arXiv.org · 80d ago Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration stat.ML updates on arXiv.org · 80d ago Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics stat.ML updates on arXiv.org · 80d ago Factor Augmented High-Dimensional SGD stat.ML updates on arXiv.org · 80d ago A Unified Framework for Structure-Aware Clustering and Heterogeneous Causal Graph Learning stat.ML updates on arXiv.org · 80d ago Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian stat.ML updates on arXiv.org · 80d ago Density-Ratio Losses for Post-Hoc Learning to Defer stat.ML updates on arXiv.org · 80d ago Posterior Contraction of L\'evy Adaptive B-spline Regression in Besov Spaces stat.ML updates on arXiv.org · 80d ago Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation stat.ML updates on arXiv.org · 80d ago Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data stat.ML updates on arXiv.org · 80d ago Probabilistic Multivariate Time Series Forecasting with Diffusion Copulas stat.ML updates on arXiv.org · 80d ago Tail Annealing for Heavy-Tailed Flow Matching stat.ML updates on arXiv.org · 80d ago Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation stat.ML updates on arXiv.org · 80d ago Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization stat.ML updates on arXiv.org · 80d ago Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis stat.ML updates on arXiv.org · 80d ago When Individually Calibrated Models Become Collectively Miscalibrated stat.ML updates on arXiv.org · 80d ago OlmoEarth v1.1: A more efficient family of models Ai2 Blog · 81d ago Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra cs.LG updates on arXiv.org · 81d ago Mirror Descent-Type Algorithms for the Variational Inequality Problem with Functional Constraints cs.LG updates on arXiv.org · 81d ago Reducing Credit Assignment Variance via Counterfactual Reasoning Paths cs.LG updates on arXiv.org · 81d ago SignMuon: Communication-Efficient Distributed Muon Optimization cs.LG updates on arXiv.org · 81d ago When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning cs.LG updates on arXiv.org · 81d ago A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning cs.LG updates on arXiv.org · 81d ago Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning cs.LG updates on arXiv.org · 81d ago Forecasting Medium-Horizon Alzheimer's Disease Progression: Residual Gap-Aware Transformers for 24-Month CDR-SB Change from ADNI Clinical and Biomarker Histories cs.LG updates on arXiv.org · 81d ago AdaGraph: A Graph-Native Clustering Algorithm That Overcomes the Curse of Dimensionality and Enables Scientific Discovery cs.LG updates on arXiv.org · 81d ago Language Game: Talking to Non-Human Systems cs.LG updates on arXiv.org · 81d ago Bi-Level Chaotic Fusion Based Graph Convolutional Network for Stock Market Prediction Interval cs.LG updates on arXiv.org · 81d ago Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry cs.LG updates on arXiv.org · 81d ago Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders cs.LG updates on arXiv.org · 81d ago Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization cs.LG updates on arXiv.org · 81d ago DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models cs.LG updates on arXiv.org · 81d ago LoopQ: Quantization for Recursive Transformers cs.LG updates on arXiv.org · 81d ago Goal-Conditioned Supervised Learning for LLM Fine-Tuning cs.LG updates on arXiv.org · 81d ago PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation cs.LG updates on arXiv.org · 81d ago HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support cs.LG updates on arXiv.org · 81d ago Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field cs.LG updates on arXiv.org · 81d ago Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures stat.ML updates on arXiv.org · 81d ago StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow stat.ML updates on arXiv.org · 81d ago Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models stat.ML updates on arXiv.org · 81d ago Prediction-Intervention Games and Invariant Sets stat.ML updates on arXiv.org · 81d ago HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations stat.ML updates on arXiv.org · 81d ago A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights stat.ML updates on arXiv.org · 81d ago CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series stat.ML updates on arXiv.org · 81d ago Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations stat.ML updates on arXiv.org · 81d ago Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and Safety stat.ML updates on arXiv.org · 81d ago Sample efficient inductive matrix completion with noise and inexact side information stat.ML updates on arXiv.org · 81d ago On Gaussian approximation for entropy-regularized Q-learning with function approximation stat.ML updates on arXiv.org · 81d ago Online Conformal Prediction for Non-Exchangeable Panel Data stat.ML updates on arXiv.org · 81d ago How does feature learning reshape the function space? stat.ML updates on arXiv.org · 81d ago StatQAT: Statistical Quantizer Optimization for Deep Networks stat.ML updates on arXiv.org · 81d ago Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent stat.ML updates on arXiv.org · 81d ago Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures stat.ML updates on arXiv.org · 81d ago A data-driven Fourier-mixture neural-network method for density estimation stat.ML updates on arXiv.org · 81d ago A note on connections between the F\"ollmer process and the denoising diffusion probabilistic model stat.ML updates on arXiv.org · 81d ago Wasserstein bounds for denoising diffusion probabilistic models via the F\"ollmer process stat.ML updates on arXiv.org · 81d ago Canonical Regularisation of Wide Feature-Learning Neural Networks stat.ML updates on arXiv.org · 81d ago AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices cs.LG updates on arXiv.org · 82d ago TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination cs.LG updates on arXiv.org · 82d ago Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels cs.LG updates on arXiv.org · 82d ago Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation cs.LG updates on arXiv.org · 82d ago MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion cs.LG updates on arXiv.org · 82d ago Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation cs.LG updates on arXiv.org · 82d ago Logical Grammar Induction via Graph Kolmogorov Complexity: A Neuro-Symbolic Framework for Self-Healing Clinical Data Integrity cs.LG updates on arXiv.org · 82d ago Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design cs.LG updates on arXiv.org · 82d ago Privacy Evaluation of Generative Models for Trajectory Generation cs.LG updates on arXiv.org · 82d ago GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding cs.LG updates on arXiv.org · 82d ago PDRNN: Modular Data-driven Pedestrian Dead Reckoning on Loosely Coupled Radio- and Inertial-Signalstreams cs.LG updates on arXiv.org · 82d ago Position: Ideas Should be the Center of Machine Learning Research cs.LG updates on arXiv.org · 82d ago Curriculum Learning of Physics-Informed Neural Networks based on Spatial Correlation cs.LG updates on arXiv.org · 82d ago Training on Documents About Monitoring Leads to CoT Obfuscation cs.LG updates on arXiv.org · 82d ago Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning cs.LG updates on arXiv.org · 82d ago Universal Approximation of Nonlinear Operators and Their Derivatives cs.LG updates on arXiv.org · 82d ago GQA-{\mu}P: The maximal parameterization update for grouped query attention cs.LG updates on arXiv.org · 82d ago GESD: Beyond Outcome-Oriented Fairness cs.LG updates on arXiv.org · 82d ago How Data Augmentation Shapes Neural Representations cs.LG updates on arXiv.org · 82d ago Time-Varying Deep State Space Models for Sequences with Switching Dynamics cs.LG updates on arXiv.org · 82d ago On Kernel Eigen-alignments of KRR: Reconstruction and Generalization stat.ML updates on arXiv.org · 82d ago Harnessing Unimodality in Semiparametric Contextual Pricing via Oracle Price Map Learning stat.ML updates on arXiv.org · 82d ago MaxSketch: Robust Distinct Counting in Streams via Random Projections stat.ML updates on arXiv.org · 82d ago Pessimistic Risk-Aware Policy Learning in Contextual Bandits stat.ML updates on arXiv.org · 82d ago $\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors stat.ML updates on arXiv.org · 82d ago Unsupervised Domain Shift Detection with Interpretable Subspace Attribution stat.ML updates on arXiv.org · 82d ago Testing properties of trees in graphical models with covariance queries stat.ML updates on arXiv.org · 82d ago Explainable AI Isn't Enough! Rethinking Algorithmic Contestability stat.ML updates on arXiv.org · 82d ago A numerical study into neural network surrogate model performance for uncertainty propagation stat.ML updates on arXiv.org · 82d ago Skew-adaptive conformal prediction stat.ML updates on arXiv.org · 82d ago A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature stat.ML updates on arXiv.org · 82d ago How Data Augmentation Shapes Neural Representations stat.ML updates on arXiv.org · 82d ago Proposal-Guided Greedy Surrogate Refinement for PDE-Driven High-Dimensional Rare-Event Estimation stat.ML updates on arXiv.org · 82d ago Representation Without Reward: A JEPA Audit for LLM Fine-Tuning stat.ML updates on arXiv.org · 82d ago $\phi$-Balancing for Mixture-of-Experts Training stat.ML updates on arXiv.org · 82d ago Reasoning Models Don't Just Think Longer, They Move Differently stat.ML updates on arXiv.org · 82d ago Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics stat.ML updates on arXiv.org · 82d ago Improving the Efficiency of Subgroup Analysis in Randomized Controlled Trials with TMLE stat.ML updates on arXiv.org · 82d ago SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference stat.ML updates on arXiv.org · 82d ago Leveraging heterogeneity for identifiability: Bayesian order-based learning of multiple DAGs stat.ML updates on arXiv.org · 82d ago Making LLMs faster without sacrificing accuracy Amazon Science homepage · 84d ago Vision-Based Runtime Monitoring under Varying Specifications using Semantic Latent Representations cs.LG updates on arXiv.org · 85d ago Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders cs.LG updates on arXiv.org · 85d ago Rethinking Molecular OOD Generalization via Target-Aware Source Selection cs.LG updates on arXiv.org · 85d ago Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling cs.LG updates on arXiv.org · 85d ago Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models cs.LG updates on arXiv.org · 85d ago Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning cs.LG updates on arXiv.org · 85d ago EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents cs.LG updates on arXiv.org · 85d ago EMA: Efficient Model Adaptation for Learning-based Systems cs.LG updates on arXiv.org · 85d ago A Unified Geometric Framework for Weighted Contrastive Learning cs.LG updates on arXiv.org · 85d ago Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction cs.LG updates on arXiv.org · 85d ago WarmPrior: Straightening Flow-Matching Policies with Temporal Priors cs.LG updates on arXiv.org · 85d ago Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines cs.LG updates on arXiv.org · 85d ago TabPFN-3: Technical Report cs.LG updates on arXiv.org · 85d ago Neural Fields for NV-Center Inverse Sensing cs.LG updates on arXiv.org · 85d ago HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts cs.LG updates on arXiv.org · 85d ago Support Before Frequency in Discrete Diffusion cs.LG updates on arXiv.org · 85d ago Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signal cs.LG updates on arXiv.org · 85d ago R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning cs.LG updates on arXiv.org · 85d ago Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility cs.LG updates on arXiv.org · 85d ago Reliability-Gated Source Anchoring for Continual Test-Time Adaptation cs.LG updates on arXiv.org · 85d ago AIS: Adaptive Importance Sampling for Quantized RL stat.ML updates on arXiv.org · 85d ago Covariance-aware sampling for Diffusion Models stat.ML updates on arXiv.org · 85d ago A Survey on Data-Dependent Worst-Case Generalization Bounds stat.ML updates on arXiv.org · 85d ago Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference stat.ML updates on arXiv.org · 85d ago A Regret Perspective on Online Multiple Testing stat.ML updates on arXiv.org · 85d ago Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning stat.ML updates on arXiv.org · 85d ago To discretize continually: Mean shift interacting particle systems for Bayesian inference stat.ML updates on arXiv.org · 85d ago On the Burden of Achieving Fairness in Conformal Prediction stat.ML updates on arXiv.org · 85d ago Training-Free Generative Sampling via Moment-Matched Score Smoothing stat.ML updates on arXiv.org · 85d ago Large Dimensional Kernel Ridge Regression: Extending to Product Kernels stat.ML updates on arXiv.org · 85d ago Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model stat.ML updates on arXiv.org · 85d ago K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles stat.ML updates on arXiv.org · 85d ago Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models stat.ML updates on arXiv.org · 85d ago From Data to Action: Accelerating Refinery Optimization with AI stat.ML updates on arXiv.org · 85d ago Logging Policy Design for Off-Policy Evaluation stat.ML updates on arXiv.org · 85d ago RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution stat.ML updates on arXiv.org · 85d ago Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling stat.ML updates on arXiv.org · 85d ago Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm stat.ML updates on arXiv.org · 85d ago TabPFN-3: Technical Report stat.ML updates on arXiv.org · 85d ago Finite-size scaling of hetero-associative retrieval in continuous-signal-driven Ising spin systems stat.ML updates on arXiv.org · 85d ago Promptimus: Improving already good LLM prompts with zero manual engineering Amazon Science homepage · 85d ago Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance cs.LG updates on arXiv.org · 86d ago CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks cs.LG updates on arXiv.org · 86d ago Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity cs.LG updates on arXiv.org · 86d ago OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting cs.LG updates on arXiv.org · 86d ago Learning to Decide with AI Assistance under Human-Alignment cs.LG updates on arXiv.org · 86d ago Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise cs.LG updates on arXiv.org · 86d ago Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic cs.LG updates on arXiv.org · 86d ago Multi-Rollout On-Policy Distillation via Peer Successes and Failures cs.LG updates on arXiv.org · 86d ago Plan Before You Trade: Inference-Time Optimization for RL Trading Agents cs.LG updates on arXiv.org · 86d ago scShapeBench: Discovering geometry from high dimensional scRNAseq data cs.LG updates on arXiv.org · 86d ago ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization cs.LG updates on arXiv.org · 86d ago Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction cs.LG updates on arXiv.org · 86d ago A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions cs.LG updates on arXiv.org · 86d ago IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback cs.LG updates on arXiv.org · 86d ago Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification cs.LG updates on arXiv.org · 86d ago UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning cs.LG updates on arXiv.org · 86d ago Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions cs.LG updates on arXiv.org · 86d ago Early Data Exposure Improves Robustness to Subsequent Fine-Tuning cs.LG updates on arXiv.org · 86d ago A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data cs.LG updates on arXiv.org · 86d ago Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations cs.LG updates on arXiv.org · 86d ago Online Conformal Prediction: Enforcing monotonicity via Online Optimization stat.ML updates on arXiv.org · 86d ago A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention stat.ML updates on arXiv.org · 86d ago ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks stat.ML updates on arXiv.org · 86d ago Robust Sequential Experimental Design for A/B Testing stat.ML updates on arXiv.org · 86d ago The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge stat.ML updates on arXiv.org · 86d ago When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems stat.ML updates on arXiv.org · 86d ago Coreset-Induced Conditional Velocity Flow Matching stat.ML updates on arXiv.org · 86d ago Adaptive Kernel Density Estimation with Pre-training stat.ML updates on arXiv.org · 86d ago State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives stat.ML updates on arXiv.org · 86d ago Amortized Neural Clustering of Time Series based on Statistical Features stat.ML updates on arXiv.org · 86d ago On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods stat.ML updates on arXiv.org · 86d ago Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process stat.ML updates on arXiv.org · 86d ago Kernel-based guarantees for nonlinear parametric models in Bayesian optimization stat.ML updates on arXiv.org · 86d ago Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems stat.ML updates on arXiv.org · 86d ago LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information stat.ML updates on arXiv.org · 86d ago The Sample Complexity of Multiple Change Point Identification under Bandit Feedback stat.ML updates on arXiv.org · 86d ago Learning Perturbations to Extrapolate Your LLM stat.ML updates on arXiv.org · 86d ago On the Limits of Latent Reuse in Diffusion Models stat.ML updates on arXiv.org · 86d ago Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models stat.ML updates on arXiv.org · 86d ago Causal Learning with the Invariance Principle stat.ML updates on arXiv.org · 86d ago Introducing AIMIP: The AI weather and climate model intercomparison project Ai2 Blog · 87d ago Interpretable EEG Microstate Discovery via Variational Deep Embedding: A Systematic Architecture Search with Multi-Quadrant Evaluation cs.LG updates on arXiv.org · 87d ago QuIDE: Mastering the Quantized Intelligence Trade-off via Active Optimization cs.LG updates on arXiv.org · 87d ago Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models cs.LG updates on arXiv.org · 87d ago Rotation-Preserving Supervised Fine-Tuning cs.LG updates on arXiv.org · 87d ago Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization cs.LG updates on arXiv.org · 87d ago Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation cs.LG updates on arXiv.org · 87d ago LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection cs.LG updates on arXiv.org · 87d ago $\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin cs.LG updates on arXiv.org · 87d ago TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment cs.LG updates on arXiv.org · 87d ago Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioning cs.LG updates on arXiv.org · 87d ago AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines cs.LG updates on arXiv.org · 87d ago Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation cs.LG updates on arXiv.org · 87d ago SURGE: Surrogate Gradient Adaptation in Binary Neural Networks cs.LG updates on arXiv.org · 87d ago Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures cs.LG updates on arXiv.org · 87d ago SkillGen: Verified Inference-Time Agent Skill Synthesis cs.LG updates on arXiv.org · 87d ago Finite Volume-Informed Neural Network Framework for 2D Shallow Water Equations: Rugged Loss Landscapes and the Importance of Data Guidance cs.LG updates on arXiv.org · 87d ago DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism cs.LG updates on arXiv.org · 87d ago RT-Transformer: The Transformer Block as a Spherical State Estimator cs.LG updates on arXiv.org · 87d ago When and How to Canonize: A Generalization Perspective cs.LG updates on arXiv.org · 87d ago ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network cs.LG updates on arXiv.org · 87d ago Uniform Scaling Limits in AdamW-Trained Transformers stat.ML updates on arXiv.org · 87d ago Interpretable Machine Learning for Spatial Science: A Lie-Algebraic Kernel for Rotationally Anisotropic Gaussian Processes stat.ML updates on arXiv.org · 87d ago Adaptive Policy Learning Under Unknown Network Interference stat.ML updates on arXiv.org · 87d ago Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors stat.ML updates on arXiv.org · 87d ago Post-ADC Inference: Valid Inference After Active Data Collection stat.ML updates on arXiv.org · 87d ago Exact Stiefel Optimization for Probabilistic PLS: Closed-Form Updates, Error Bounds, and Calibrated Uncertainty stat.ML updates on arXiv.org · 87d ago Learning U-Statistics with Active Inference stat.ML updates on arXiv.org · 87d ago Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces stat.ML updates on arXiv.org · 87d ago Minimax Rates and Spectral Distillation for Tree Ensembles stat.ML updates on arXiv.org · 87d ago Variance-aware Reward Modeling with Anchor Guidance stat.ML updates on arXiv.org · 87d ago Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions stat.ML updates on arXiv.org · 87d ago Information-Theoretic Generalization Bounds for Sequential Decision Making stat.ML updates on arXiv.org · 87d ago Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification stat.ML updates on arXiv.org · 87d ago Optimal Policy Learning under Budget and Coverage Constraints stat.ML updates on arXiv.org · 87d ago Online Learning-to-Defer with Varying Experts stat.ML updates on arXiv.org · 87d ago Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting stat.ML updates on arXiv.org · 87d ago Model-based Bootstrap of Controlled Markov Chains stat.ML updates on arXiv.org · 87d ago Testing General Relativity Through Gravitational Wave Classification: A Convolutional Neural Network Framework stat.ML updates on arXiv.org · 87d ago Sensor Design for Accuracy-Bounded Estimation via Maximum-Entropy Likelihood Synthesis stat.ML updates on arXiv.org · 87d ago Variational predictive resampling stat.ML updates on arXiv.org · 87d ago Reinforcement learning for inverse structural design and rapid laser cutting of kirigami prototypes cs.LG updates on arXiv.org · 88d ago Path-Based Gradient Boosting for Graph-Level Prediction cs.LG updates on arXiv.org · 88d ago Distributional Reinforcement Learning via the Cram\'er Distance cs.LG updates on arXiv.org · 88d ago Geometry-free prediction of inertial lift forces in microfluidic devices using deep learning cs.LG updates on arXiv.org · 88d ago BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models cs.LG updates on arXiv.org · 88d ago TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data cs.LG updates on arXiv.org · 88d ago Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa cs.LG updates on arXiv.org · 88d ago Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant cs.LG updates on arXiv.org · 88d ago The Safety-Aware Denoiser for Text Diffusion Models cs.LG updates on arXiv.org · 88d ago Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking cs.LG updates on arXiv.org · 88d ago Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge cs.LG updates on arXiv.org · 88d ago Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models cs.LG updates on arXiv.org · 88d ago Towards Customized Multimodal Role-Play cs.LG updates on arXiv.org · 88d ago Additive Atomic Forests for Symbolic Function and Antiderivative Discovery cs.LG updates on arXiv.org · 88d ago Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization cs.LG updates on arXiv.org · 88d ago DARE: Diffusion Language Model Activation Reuse for Efficient Inference cs.LG updates on arXiv.org · 88d ago Dendritic Neural Networks with Equilibrium Propagation cs.LG updates on arXiv.org · 88d ago Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI cs.LG updates on arXiv.org · 88d ago DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis cs.LG updates on arXiv.org · 88d ago Reasoning emerges from constrained inference manifolds in large language models cs.LG updates on arXiv.org · 88d ago Decentralized Conformal Novelty Detection via Quantized Model Exchange stat.ML updates on arXiv.org · 88d ago Active Multiple-Prediction-Powered Inference stat.ML updates on arXiv.org · 88d ago Sinkhorn Treatment Effects: A Causal Optimal Transport Measure stat.ML updates on arXiv.org · 88d ago Sliced Inner Product Gromov-Wasserstein Distances stat.ML updates on arXiv.org · 88d ago Learnability and Competition in High-Dimensional Multi-Component ICA stat.ML updates on arXiv.org · 88d ago CONTRA: Conformal Prediction Region via Normalizing Flow Transformation stat.ML updates on arXiv.org · 88d ago Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems stat.ML updates on arXiv.org · 88d ago Measuring and Decomposing Mode Separation via the Canonical Diffusion stat.ML updates on arXiv.org · 88d ago Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity stat.ML updates on arXiv.org · 88d ago Tight Generalization Bounds for Noiseless Inverse Optimization stat.ML updates on arXiv.org · 88d ago Survey-aware Machine Learning: A Guideline for Valid Population Health Inference based on Scoping Review stat.ML updates on arXiv.org · 88d ago Optimality of Sub-network Laplace Approximations: New Results and Methods stat.ML updates on arXiv.org · 88d ago Optimal Regret for Single Index Bandits stat.ML updates on arXiv.org · 88d ago Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow stat.ML updates on arXiv.org · 88d ago Empirical Bayes 1-bit matrix completion stat.ML updates on arXiv.org · 88d ago Metropolis-Adjusted Diffusion Models stat.ML updates on arXiv.org · 88d ago Learning stochastic multiscale models through normalizing flows stat.ML updates on arXiv.org · 88d ago Supercharging Bayesian Inference with Reliable AI-Informed Priors stat.ML updates on arXiv.org · 88d ago Unified Approach for Weakly Supervised Multicalibration stat.ML updates on arXiv.org · 88d ago Federated Language Models Under Bandwidth Budgets: Distillation Rates and Conformal Coverage stat.ML updates on arXiv.org · 88d ago Why Artificial Analysis uses Ai2's IFBench instruction-following eval Ai2 Blog · 89d ago RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory cs.LG updates on arXiv.org · 89d ago LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction cs.LG updates on arXiv.org · 89d ago A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence cs.LG updates on arXiv.org · 89d ago Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding cs.LG updates on arXiv.org · 89d ago On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching cs.LG updates on arXiv.org · 89d ago A Hierarchical Ensemble Pipeline for Anomaly Detection in ESA Satellite Telemetry cs.LG updates on arXiv.org · 89d ago Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models cs.LG updates on arXiv.org · 89d ago From Canopy to Collision: A Hybrid Predictive Framework for Identifying Risk Factors in Tree-Involved Traffic Crashes cs.LG updates on arXiv.org · 89d ago Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices cs.LG updates on arXiv.org · 89d ago Conditional generation of antibody sequences with classifier-guided germline-absorbing discrete diffusion cs.LG updates on arXiv.org · 89d ago Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning cs.LG updates on arXiv.org · 89d ago Transformer-Based Wildlife Species Classification from Daily Movement Trajectories cs.LG updates on arXiv.org · 89d ago Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training cs.LG updates on arXiv.org · 89d ago The E$\Delta$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality cs.LG updates on arXiv.org · 89d ago Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics cs.LG updates on arXiv.org · 89d ago On Training in Imagination cs.LG updates on arXiv.org · 89d ago Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA cs.LG updates on arXiv.org · 89d ago Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning cs.LG updates on arXiv.org · 89d ago STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification cs.LG updates on arXiv.org · 89d ago Geometric Kolmogorov--Arnold Network (GeoKAN) cs.LG updates on arXiv.org · 89d ago How Does Attention Help? Insights from Random Matrices on Signal Recovery from Sequence Models stat.ML updates on arXiv.org · 89d ago One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators stat.ML updates on arXiv.org · 89d ago Kernel Selection is Model Selection: A Unified Complexity-Penalized Approach for MMD Two-Sample Tests stat.ML updates on arXiv.org · 89d ago Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions stat.ML updates on arXiv.org · 89d ago A Differentiable Bayesian Relaxation for Latent Partial-Order Inference stat.ML updates on arXiv.org · 89d ago BGM-IV: an AI-powered Bayesian generative modeling approach for instrumental variable analysis stat.ML updates on arXiv.org · 89d ago An Interpretable and Scalable Framework for Evaluating Large Language Models stat.ML updates on arXiv.org · 89d ago Causal EpiNets: Precision-corrected Bounds on Individual Treatment Effects using Epistemic Neural Networks stat.ML updates on arXiv.org · 89d ago Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity stat.ML updates on arXiv.org · 89d ago TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models stat.ML updates on arXiv.org · 89d ago Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples stat.ML updates on arXiv.org · 89d ago Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers stat.ML updates on arXiv.org · 89d ago A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning stat.ML updates on arXiv.org · 89d ago Reliable Chain-of-Thought via Prefix Consistency stat.ML updates on arXiv.org · 89d ago Debiased Counterfactual Generation via Flow Matching from Observations stat.ML updates on arXiv.org · 89d ago TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information stat.ML updates on arXiv.org · 89d ago Flow Matching for Count Data stat.ML updates on arXiv.org · 89d ago Expectation-Maximization as a Spectrally Governed Relaxation Flow stat.ML updates on arXiv.org · 89d ago Characterizing and Correcting Effective Target Shift in Online Learning stat.ML updates on arXiv.org · 89d ago Consistency Regularised Gradient Flows for Inverse Problems stat.ML updates on arXiv.org · 89d ago Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling The Berkeley Artificial Intelligence Research Blog · 92d ago EMO: Pretraining mixture of experts for emergent modularity Ai2 Blog · 92d ago Are Flat Minima an Illusion? cs.LG updates on arXiv.org · 92d ago Nationwide EHR-Based Chronic Rhinosinusitis Prediction Using Demographic-Stratified Models cs.LG updates on arXiv.org · 92d ago SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees cs.LG updates on arXiv.org · 92d ago Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning cs.LG updates on arXiv.org · 92d ago Horizon-Constrained Rashomon Sets for Chaotic Forecasting cs.LG updates on arXiv.org · 92d ago Sparse Prefix Caching for Hybrid and Recurrent LLM Serving cs.LG updates on arXiv.org · 92d ago MidSteer: Optimal Affine Framework for Steering Generative Models cs.LG updates on arXiv.org · 92d ago Data-Driven Variational Basis Learning Beyond Neural Networks: A Non-Neural Framework for Adaptive Basis Discovery cs.LG updates on arXiv.org · 92d ago Adaptive Computation Depth via Learned Token Routing in Transformers cs.LG updates on arXiv.org · 92d ago Structural Instability of Feature Composition cs.LG updates on arXiv.org · 92d ago Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms cs.LG updates on arXiv.org · 92d ago MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference cs.LG updates on arXiv.org · 92d ago Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning cs.LG updates on arXiv.org · 92d ago Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods cs.LG updates on arXiv.org · 92d ago Evolutionary fine tuning of quantized convolution-based deep learning models cs.LG updates on arXiv.org · 92d ago Expert Routing for Communication-Efficient MoE via Finite Expert Banks cs.LG updates on arXiv.org · 92d ago Forecasting Green Skill Demand in the Automotive Industry: Evidence from Online Job Postings cs.LG updates on arXiv.org · 92d ago Attribution-Guided Continual Learning for Large Language Models cs.LG updates on arXiv.org · 92d ago Graph Normalization: Fast Binarizing Dynamics for Differentiable MWIS cs.LG updates on arXiv.org · 92d ago Feature Starvation as Geometric Instability in Sparse Autoencoders cs.LG updates on arXiv.org · 92d ago Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning stat.ML updates on arXiv.org · 92d ago Forecasting Oncology Demand Trends with Boosting-Based Bayesian Conjugate Models stat.ML updates on arXiv.org · 92d ago Estimating Implicit Regularization in Deep Learning stat.ML updates on arXiv.org · 92d ago Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation stat.ML updates on arXiv.org · 92d ago Permutation-preserving Functions and Neural Vecchia Covariance Kernels stat.ML updates on arXiv.org · 92d ago Relaxed Sparsest-Permutation Formulation for Causal Discovery at Scale stat.ML updates on arXiv.org · 92d ago In-Context Positive-Unlabeled Learning stat.ML updates on arXiv.org · 92d ago Variational Smoothing and Inference for SDEs from Sparse Data with Dynamic Neural Flows stat.ML updates on arXiv.org · 92d ago Spherical Flows for Sampling Categorical Data stat.ML updates on arXiv.org · 92d ago Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization stat.ML updates on arXiv.org · 92d ago Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring and FFCI Testing in Mixed Data stat.ML updates on arXiv.org · 92d ago Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement stat.ML updates on arXiv.org · 92d ago Ratio-based Loss Functions stat.ML updates on arXiv.org · 92d ago CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency stat.ML updates on arXiv.org · 92d ago Tuning Derivatives for Causal Fairness in Machine Learning stat.ML updates on arXiv.org · 92d ago Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking stat.ML updates on arXiv.org · 92d ago TabCF: Distributional Control Function Estimation with Tabular Foundation Models stat.ML updates on arXiv.org · 92d ago Gaussian mixture models in Hilbert spaces via kernel methods stat.ML updates on arXiv.org · 92d ago Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective stat.ML updates on arXiv.org · 92d ago When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination stat.ML updates on arXiv.org · 92d ago Open by design: Ai2 brings fully open AI infrastructure online with NSF OMAI Ai2 Blog · 93d ago Endogenous Regime Switching Driven by Scalar-Irreducible Learning Dynamics cs.LG updates on arXiv.org · 93d ago A Self-Attentive Meta-Optimizer with Group-Adaptive Learning Rates and Weight Decay cs.LG updates on arXiv.org · 93d ago Transformation Categorization Based on Group Decomposition Theory Using Parameter Division cs.LG updates on arXiv.org · 93d ago Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search cs.LG updates on arXiv.org · 93d ago MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning cs.LG updates on arXiv.org · 93d ago Continual Distillation of Teachers from Different Domains cs.LG updates on arXiv.org · 93d ago Lookahead Drifting Model cs.LG updates on arXiv.org · 93d ago Single-Position Intervention Fails: Distributed Output Templates Drive In-Context Learning cs.LG updates on arXiv.org · 93d ago EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation cs.LG updates on arXiv.org · 93d ago Investigating Trustworthiness of Nonparametric Deep Survival Models for Alzheimer's Disease Progression Analysis cs.LG updates on arXiv.org · 93d ago Improving Medical VQA through Trajectory-Aware Process Supervision cs.LG updates on arXiv.org · 93d ago Designing a double deep reinforcement learning selection tool for resilient demand prediction cs.LG updates on arXiv.org · 93d ago LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment cs.LG updates on arXiv.org · 93d ago FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing cs.LG updates on arXiv.org · 93d ago Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction cs.LG updates on arXiv.org · 93d ago Confronting Label Indeterminacy in Automated Bail Decisions cs.LG updates on arXiv.org · 93d ago A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers cs.LG updates on arXiv.org · 93d ago RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction cs.LG updates on arXiv.org · 93d ago A Regulatory Governance Framework for AI-Driven Financial Fraud Detection in U.S. Banking: Integrating OCC, SR 11-7, CFPB, and FinCEN Compliance Requirements for Model Development, Validation, and Monitoring Lifecycles cs.LG updates on arXiv.org · 93d ago Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO cs.LG updates on arXiv.org · 93d ago A Consistency-Centric Approach to Set-Based Optimization with Multiple Models of Unranked Fidelity stat.ML updates on arXiv.org · 93d ago Heterogeneous Ordinal Structure Learning with Bayesian Nonparametric Complexity Discovery stat.ML updates on arXiv.org · 93d ago Entropic Riemannian Neural Optimal Transport stat.ML updates on arXiv.org · 93d ago Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization stat.ML updates on arXiv.org · 93d ago Perturbation is All You Need for Extrapolating Language Models stat.ML updates on arXiv.org · 93d ago Multiscale Euclidean Network Trajectories: Second-Moment Geometry, Attribution, and Change Points stat.ML updates on arXiv.org · 93d ago Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift stat.ML updates on arXiv.org · 93d ago Scalable inference of spatial regions and temporal signatures from time series stat.ML updates on arXiv.org · 93d ago Hypergraph Generation via Structured Stochastic Diffusion stat.ML updates on arXiv.org · 93d ago Proximal Projection for Doubly Sparse Regularized Models stat.ML updates on arXiv.org · 93d ago Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval stat.ML updates on arXiv.org · 93d ago Bayesian Optimization in Linear Time stat.ML updates on arXiv.org · 93d ago BOOOM: Loss-Function-Agnostic Black-Box Optimization over Orthonormal Manifolds for Machine Learning and Statistical Inference stat.ML updates on arXiv.org · 93d ago Explaining and Preventing Alignment Collapse in Iterative RLHF stat.ML updates on arXiv.org · 93d ago A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning stat.ML updates on arXiv.org · 93d ago Symbolic Regression via Neural Networks stat.ML updates on arXiv.org · 93d ago Causal discovery under mean independence and linearity stat.ML updates on arXiv.org · 93d ago Augmented transfer regression learning for completely missing covariates stat.ML updates on arXiv.org · 93d ago FL-Sailer: Efficient and Privacy-Preserving Federated Learning for Scalable Single-Cell Epigenetic Data Analysis via Adaptive Sampling stat.ML updates on arXiv.org · 93d ago From Video-to-PDE: Data-Driven Discovery of Nonlinear Dye Plume Dynamics stat.ML updates on arXiv.org · 93d ago Navigating uncertainty in Amazon's middle-mile network Amazon Science homepage · 93d ago StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing cs.LG updates on arXiv.org · 94d ago eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization cs.LG updates on arXiv.org · 94d ago An End-to-End Framework for Building Large Language Models for Software Operations cs.LG updates on arXiv.org · 94d ago On the Invariants of Softmax Attention cs.LG updates on arXiv.org · 94d ago Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR cs.LG updates on arXiv.org · 94d ago Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Models cs.LG updates on arXiv.org · 94d ago Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning cs.LG updates on arXiv.org · 94d ago When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models cs.LG updates on arXiv.org · 94d ago From Synthesis to Clinical Assistance: A Strategy-Aware Agent Framework for Autism Intervention based on Real Clinical Dataset cs.LG updates on arXiv.org · 94d ago PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL cs.LG updates on arXiv.org · 94d ago Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection cs.LG updates on arXiv.org · 94d ago Heterogeneous Graph Importance Scoring and Clustering with Automated LLM-based Interpretation cs.LG updates on arXiv.org · 94d ago DeRelayL: Sustainable Decentralized Relay Learning cs.LG updates on arXiv.org · 94d ago Proteo-R1: Reasoning Foundation Models for De Novo Protein Design cs.LG updates on arXiv.org · 94d ago PAMNet: Cycle-aware Phase-Amplitude Modulation Network for Multivariate Time Series Forecasting cs.LG updates on arXiv.org · 94d ago From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework cs.LG updates on arXiv.org · 94d ago PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework cs.LG updates on arXiv.org · 94d ago A Framework for Exploring and Disentangling Intersectional Bias: A Case Study in Fetal Ultrasound cs.LG updates on arXiv.org · 94d ago Healthcare AI GYM for Medical Agents cs.LG updates on arXiv.org · 94d ago Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation cs.LG updates on arXiv.org · 94d ago Dynamic Vine Copulas: Detecting and Quantifying Time-Varying Higher-Order Interactions stat.ML updates on arXiv.org · 94d ago Conformalized Percentile Interval: Finite Sample Validity and Improved Conditional Performance stat.ML updates on arXiv.org · 94d ago Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancy stat.ML updates on arXiv.org · 94d ago Partial Effective Information Decomposition for Synergistic Causality stat.ML updates on arXiv.org · 94d ago On the Spectral Structure and Objective Equivalence of Orthogonal Multilabel Fisher Discriminants stat.ML updates on arXiv.org · 94d ago Imbalanced Classification under Capacity Constraints stat.ML updates on arXiv.org · 94d ago Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity stat.ML updates on arXiv.org · 94d ago Stochastic Schr\"odinger Diffusion Models for Pure-State Ensemble Generation stat.ML updates on arXiv.org · 94d ago Free Decompression with Algebraic Spectral Curves stat.ML updates on arXiv.org · 94d ago Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification stat.ML updates on arXiv.org · 94d ago Tempered Guided Diffusion stat.ML updates on arXiv.org · 94d ago Predicting missing values: A good idea? stat.ML updates on arXiv.org · 94d ago Low Rank Tensor Completion via Adaptive ADMM stat.ML updates on arXiv.org · 94d ago Training-Free Probabilistic Time-Series Forecasting with Conformal Seasonal Pools stat.ML updates on arXiv.org · 94d ago The Manokhin Probability Matrix: A Diagnostic Framework for Classifier Probability Quality stat.ML updates on arXiv.org · 94d ago Conditional Diffusion Sampling stat.ML updates on arXiv.org · 94d ago Analysis and Explainability of LLMs Via Evolutionary Methods stat.ML updates on arXiv.org · 94d ago Disease Is a Spectral Perturbation stat.ML updates on arXiv.org · 94d ago ISAAC: Auditing Causal Reasoning in Deep Models for Drug-Target Interaction stat.ML updates on arXiv.org · 94d ago Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach stat.ML updates on arXiv.org · 94d ago White House working group on AI – Statement from FLI’s Anthony Aguirre Future of Life Institute · 94d ago How mechanism design theory helps optimize Amazon-vendor collaboration Amazon Science homepage · 94d ago MolmoAct 2: An open foundation for robots that work in the real world Ai2 Blog · 95d ago Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling cs.LG updates on arXiv.org · 95d ago Polynomial-Time Optimal Group Selection via the Double-Commutator Eigenvalue Problem cs.LG updates on arXiv.org · 95d ago Sparse Regression under Correlation and Weak Signals: A Reproducible Benchmark of Classical and Bayesian Methods cs.LG updates on arXiv.org · 95d ago From Euler to Dormand-Prince: ODE Solvers for Flow Matching Generative Models cs.LG updates on arXiv.org · 95d ago Fast Log-Domain Sinkhorn Optimal Transport with Warp-Level GPU Reductions cs.LG updates on arXiv.org · 95d ago GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI cs.LG updates on arXiv.org · 95d ago StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer cs.LG updates on arXiv.org · 95d ago Linking spatial biology and clinical histology via Haiku cs.LG updates on arXiv.org · 95d ago A Review of the Receiver Operating Characteristic Curve and a Proof About the Area Beneath It cs.LG updates on arXiv.org · 95d ago PhaseNet++: Phase-Aware Frequency-Domain Anomaly Detection for Industrial Control Systems via Phase Coherence Graphs cs.LG updates on arXiv.org · 95d ago Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design cs.LG updates on arXiv.org · 95d ago CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining cs.LG updates on arXiv.org · 95d ago Structured Analytic Coherent Point Drift for Non-Rigid Point Set Registration cs.LG updates on arXiv.org · 95d ago Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding cs.LG updates on arXiv.org · 95d ago EventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems cs.LG updates on arXiv.org · 95d ago Fusing Urban Structure and Semantics: A Conditional Diffusion Model for Cross-City OD Matrix Generation cs.LG updates on arXiv.org · 95d ago From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity cs.LG updates on arXiv.org · 95d ago Interpretable experiential learning based on state history and global feedback cs.LG updates on arXiv.org · 95d ago Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching cs.LG updates on arXiv.org · 95d ago Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey cs.LG updates on arXiv.org · 95d ago Mean Testing under Truncation beyond Gaussian stat.ML updates on arXiv.org · 95d ago Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation stat.ML updates on arXiv.org · 95d ago Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression stat.ML updates on arXiv.org · 95d ago PRCD-MAP: Learning How Much to Trust Imperfect Priors in Causal Discovery stat.ML updates on arXiv.org · 95d ago Missingness-aware Data Imputation via AI-powered Bayesian Generative Modeling stat.ML updates on arXiv.org · 95d ago Distributional Causal Mediation via Conditional Generative Modeling stat.ML updates on arXiv.org · 95d ago A Semi-Supervised Kernel Two-Sample Test stat.ML updates on arXiv.org · 95d ago Stable Blanket with Hidden Variables and Cycles stat.ML updates on arXiv.org · 95d ago Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality stat.ML updates on arXiv.org · 95d ago Extrapolation in Statistical Learning with Extreme Value Theory stat.ML updates on arXiv.org · 95d ago MIRA: A Score for Conditional Distribution Accuracy and Model Comparison stat.ML updates on arXiv.org · 95d ago The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy stat.ML updates on arXiv.org · 95d ago Measuring Differences between Conditional Distributions using Kernel Embeddings stat.ML updates on arXiv.org · 95d ago Active multiple matrix completion with adaptive confidence sets stat.ML updates on arXiv.org · 95d ago Middle-mile logistics through the lens of goal-conditioned reinforcement learning stat.ML updates on arXiv.org · 95d ago Black-box optimization of noisy functions with unknown smoothness stat.ML updates on arXiv.org · 95d ago Online Generalised Predictive Coding stat.ML updates on arXiv.org · 95d ago ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data stat.ML updates on arXiv.org · 95d ago Random-Effects Algorithm for Random Objects in Metric Spaces stat.ML updates on arXiv.org · 95d ago An Efficient Spatial Branch-and-Bound Algorithm for Global Optimization of Gaussian Process Posterior Mean Functions stat.ML updates on arXiv.org · 95d ago Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference cs.LG updates on arXiv.org · 96d ago FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources cs.LG updates on arXiv.org · 96d ago What Physics do Data-Driven MoCap-to-Radar Models Learn? cs.LG updates on arXiv.org · 96d ago AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G cs.LG updates on arXiv.org · 96d ago Learning physically grounded traffic accident reconstruction from public accident reports cs.LG updates on arXiv.org · 96d ago Smart Ensemble Learning Framework for Predicting Groundwater Heavy Metal Pollution cs.LG updates on arXiv.org · 96d ago Information-Theoretic Generalization Bounds for Stochastic Gradient Descent with Predictable Virtual Noise cs.LG updates on arXiv.org · 96d ago Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications cs.LG updates on arXiv.org · 96d ago Soft-MSM: Differentiable Context-Aware Elastic Alignment for Time Series cs.LG updates on arXiv.org · 96d ago CRADIPOR: Crash Dispersion Predictor cs.LG updates on arXiv.org · 96d ago Hyperspherical Forward-Forward with Prototypical Representations cs.LG updates on arXiv.org · 96d ago Comparative Analysis of Polygon-Based and Global Machine Learning Models for Bus Occupancy Prediction cs.LG updates on arXiv.org · 96d ago SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting cs.LG updates on arXiv.org · 96d ago Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization cs.LG updates on arXiv.org · 96d ago Smart Profit-Aware Crop Advisory System: Kisan AI cs.LG updates on arXiv.org · 96d ago Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization cs.LG updates on arXiv.org · 96d ago Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback cs.LG updates on arXiv.org · 96d ago Consistent Diffusion Language Models cs.LG updates on arXiv.org · 96d ago Towards A Generative Protein Evolution Machine with DPLM-Evo cs.LG updates on arXiv.org · 96d ago Introducing WARM-VR: Benchmark Dataset for Multimodal Wearable Affect Recognition in Virtual Reality cs.LG updates on arXiv.org · 96d ago Adaptive Norm-Based Regularization for Neural Networks stat.ML updates on arXiv.org · 96d ago SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contamination stat.ML updates on arXiv.org · 96d ago A unified perspective on fine-tuning and sampling with diffusion and flow models stat.ML updates on arXiv.org · 96d ago Information-geometric adaptive sampling for graph diffusion stat.ML updates on arXiv.org · 96d ago Gradient Regularized Newton Boosting Trees with Global Convergence stat.ML updates on arXiv.org · 96d ago Adaptive Querying with AI Persona Priors stat.ML updates on arXiv.org · 96d ago Decentralized Proximal Stochastic Gradient Langevin Dynamics stat.ML updates on arXiv.org · 96d ago Mean-Field Path-Integral Diffusion: From Samples to Interacting Agents stat.ML updates on arXiv.org · 96d ago Smart Ensemble Learning Framework for Predicting Groundwater Heavy Metal Pollution stat.ML updates on arXiv.org · 96d ago Provable and scalable quantum Gaussian processes for quantum learning stat.ML updates on arXiv.org · 96d ago SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting stat.ML updates on arXiv.org · 96d ago Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback stat.ML updates on arXiv.org · 96d ago OTSS: Output-Targeted Soft Segmentation for Contextual Decision-Weight Learning stat.ML updates on arXiv.org · 96d ago A Dirac-Frenkel-Onsager principle: Instantaneous residual minimization with gauge momentum for nonlinear parametrizations of PDE solutions stat.ML updates on arXiv.org · 96d ago Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity stat.ML updates on arXiv.org · 96d ago M-CaStLe: Uncovering Local Causal Structures in Multivariate Space-Time Gridded Data stat.ML updates on arXiv.org · 96d ago Optimal Spatio-Temporal Decoupling for Bayesian Conformal Prediction stat.ML updates on arXiv.org · 96d ago Concentration and Calibration in Predictive Bayesian Inference stat.ML updates on arXiv.org · 96d ago Batch Normalization for Neural Networks on Complex Domains stat.ML updates on arXiv.org · 96d ago Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation stat.ML updates on arXiv.org · 96d ago What’s next for Ai2: A conversation with Interim CEO Peter Clark Ai2 Blog · 99d ago Gradient-based Planning for World Models at Longer Horizons The Berkeley Artificial Intelligence Research Blog · 110d ago FLI’s President and CEO on Trump’s support for an AI ‘kill switch’ Future of Life Institute · 113d ago FLI CEO’s statement on the attack against Sam Altman’s home Future of Life Institute · 119d ago Prominent Scientists, Faith Leaders, Policymakers and Artists Call for a Prohibition on Superintelligence, as Poll Shows Americans Don’t Want It Future of Life Institute · 133d ago Statement: Head of US Policy on the White House AI legislative recommendations Future of Life Institute · 138d ago Identifying Interactions at Scale for LLMs The Berkeley Artificial Intelligence Research Blog · 148d ago Governor DeSantis Directs Florida State Agencies to Partner with Future of Life Institute to Shield Families from AI Harm Future of Life Institute · 151d ago “This is What it Means to be Pro-Human” Declares Broad Coalition of Conservative, Progressive, and Civil Society Groups in Statement of Shared Principles on AI Future of Life Institute · 156d ago Statement from Max Tegmark on the Department of War’s ultimatum Future of Life Institute · 162d ago The Future of Software inFERENCe · 163d ago After Orthogonality: Virtue-Ethical Agency and AI Alignment The Gradient · 170d ago Future of Life Institute Launches Multimillion Dollar Nationwide AI Regulation Campaign Future of Life Institute · 179d ago Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On inFERENCe · 188d ago NVIDIA Launches Earth-2 Family of Open Models — the World’s First Fully Open, Accelerated Set of Models and Tools for AI Weather NVIDIA Research Archives | NVIDIA Blog · 193d ago Information-Driven Design of Imaging Systems The Berkeley Artificial Intelligence Research Blog · 210d ago Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge VITALab · 214d ago AI Company Safety Practices Fall Short of Public Commitments and Show Structural Weaknesses, as Top Performers Widen the Gap Future of Life Institute · 248d ago At NeurIPS, NVIDIA Advances Open Model Development for Digital and Physical AI NVIDIA Research Archives | NVIDIA Blog · 249d ago RL without TD learning The Berkeley Artificial Intelligence Research Blog · 280d ago The U.S. Public Wants Regulation (or Prohibition) of Expert‑Level and Superhuman AI Future of Life Institute · 292d ago Michael Kleinman reacts to breakthrough AI safety legislation Future of Life Institute · 308d ago What exactly does word2vec learn? The Berkeley Artificial Intelligence Research Blog · 341d ago Brain Latent Progression Individual-based spatiotemporal disease progression on 3D Brain MRIs via latent diffusion VITALab · 345d ago How Do You Teach an AI Model to Reason? With Humans NVIDIA Research Archives | NVIDIA Blog · 345d ago A Survey of popular LLM Evaluation Metrics VITALab · 353d ago NVIDIA Research Shapes Physical AI NVIDIA Research Archives | NVIDIA Blog · 361d ago Open-Source Large Language Models in Radiology: A Review and Tutorial for Practical Research and Clinical Deployment VITALab · 362d ago Google DeepMind Falls Behind OpenAI in Latest Safety Review; All AI Companies Still Falling Short, Say Experts Future of Life Institute · 386d ago NVIDIA Research Showcases the Future of Robotics at RSS NVIDIA Research Archives | NVIDIA Blog · 413d ago NVIDIA Scores Consecutive Win for End-to-End Autonomous Driving Grand Challenge at CVPR NVIDIA Research Archives | NVIDIA Blog · 423d ago NVIDIA Research Casts New Light on Scenes With AI-Powered Rendering for Physical AI Development NVIDIA Research Archives | NVIDIA Blog · 423d ago AGI Is Not Multimodal The Gradient · 429d ago MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation VITALab · 431d ago Discrete Diffusion: Continuous-Time Markov Chains inFERENCe · 443d ago NVIDIA Research at ICLR — Pioneering the Next Wave of Multimodal Generative AI NVIDIA Research Archives | NVIDIA Blog · 470d ago Simplifying Deep Temporal Difference Learning VITALab · 488d ago EchoPrime: Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation VITALab · 502d ago Are we close to an intelligence explosion? Future of Life Institute · 504d ago Innovation to Impact: How NVIDIA Research Fuels Transformative Work in AI, Graphics and Beyond NVIDIA Research Archives | NVIDIA Blog · 506d ago NVIDIA Earth-2 Features First Gen AI to Power Weather Super-Resolution for Continental US NVIDIA Research Archives | NVIDIA Blog · 529d ago The Impact of AI in Education: Navigating the Imminent Future Future of Life Institute · 540d ago DeepSeek-V3 Technical Report VITALab · 543d ago Context and Agenda for the 2025 AI Action Summit Future of Life Institute · 553d ago Variational Autoencoders for Generating Synthetic Tractography-Based Bundle Templates in a Low-Data Setting VITALab · 571d ago NVIDIA Makes Cosmos World Foundation Models Openly Available to Physical AI Developer Community NVIDIA Research Archives | NVIDIA Blog · 578d ago Research Galore From 2024: Recapping AI Advancements in 3D Simulation, Climate Science and Audio Engineering NVIDIA Research Archives | NVIDIA Blog · 585d ago AI’s in Style: Ulta Beauty Helps Shoppers Virtually Try New Hairstyles NVIDIA Research Archives | NVIDIA Blog · 596d ago Implicit neural representations VITALab · 599d ago Crowning Achievement: NVIDIA Research Model Enables Fast, Efficient Dynamic Scene Reconstruction NVIDIA Research Archives | NVIDIA Blog · 606d ago Shape, Symmetries, and Structure: The Changing Role of Mathematics in Machine Learning Research The Gradient · 629d ago What's Missing From LLM Chatbots: A Sense of Purpose The Gradient · 697d ago We Need Positive Visions for AI Grounded in Wellbeing The Gradient · 734d ago Financial Market Applications of LLMs The Gradient · 839d ago A Brief Overview of Gender Bias in AI The Gradient · 851d ago Mamba Explained The Gradient · 863d ago Car-GPT: Could LLMs finally make self-driving cars happen? The Gradient · 882d ago Do text embeddings perfectly encode text? The Gradient · 885d ago Why Doesn’t My Model Work? The Gradient · 895d ago Deep learning for single-cell sequencing: a microscope to see the diversity of cells The Gradient · 937d ago Salmon in the Loop The Gradient · 965d ago Neural algorithmic reasoning The Gradient · 1028d ago The Artificiality of Alignment The Gradient · 1035d ago We may finally crack Maths. But should we? inFERENCe · 1156d ago Mortal Komputation: On Hinton's argument for superhuman AI. inFERENCe · 1165d ago Autoregressive Models, OOD Prompts and the Interpolation Regime inFERENCe · 1227d ago We May be Surprised Again: Why I take LLMs seriously. inFERENCe · 1234d ago Implicit Bayesian Inference in Large Language Models inFERENCe · 1618d ago Eastern European Guide to Writing Reference Letters inFERENCe · 1621d ago Causal inference 4: Causal Diagrams, Markov Factorization, Structural Equation Models inFERENCe · 1884d ago On Information Theoretic Bounds for SGD inFERENCe · 1932d ago Notes on the Origin of Implicit Regularization in SGD inFERENCe · 1954d ago An information maximization view on the $\beta$-VAE objective inFERENCe · 1968d ago Some Intuition on the Neural Tangent Kernel inFERENCe · 2086d ago Notes on Causally Correct Partial Models inFERENCe · 2094d ago
Latest
Quanta MagazineNeutrinos From Deep Inside Earth Provide a New Picture of the MantleAi2 BlogTutorMoments: Do AI tutors know when to help and when to hold back?cs.LG updates on arXiv.orgMS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classificationcs.LG updates on arXiv.orgWhen Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasterscs.LG updates on arXiv.orgPPDL: LLM-Based Flows as Probabilistic Programscs.LG updates on arXiv.orgDecoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Languagecs.LG updates on arXiv.orgDisentangling 3D Modeling from Spatial Reasoningcs.LG updates on arXiv.orgMarginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Modelscs.LG updates on arXiv.orgPRISM: Priority-aware Rubric Internalization via Structured Multimodal Data Synthesiscs.LG updates on arXiv.orgBeyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuningcs.LG updates on arXiv.orgBeyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuningcs.LG updates on arXiv.orgAn Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language Goalscs.LG updates on arXiv.orgEvaluating Machine Learning Models for Post-Wildfire Debris-Flow Predictioncs.LG updates on arXiv.orgRectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEGcs.LG updates on arXiv.orgQEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decodingcs.LG updates on arXiv.orgDG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accountingcs.LG updates on arXiv.orgQuantum-Structured World Models (QSWMs) for Predictive Latent Dynamicscs.LG updates on arXiv.orgSpectral Distillation: From Nonlinear Dynamics to Linear State-Space Modelscs.LG updates on arXiv.orgPerturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samplescs.LG updates on arXiv.orgIFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information GamesQuanta MagazineNeutrinos From Deep Inside Earth Provide a New Picture of the MantleAi2 BlogTutorMoments: Do AI tutors know when to help and when to hold back?cs.LG updates on arXiv.orgMS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classificationcs.LG updates on arXiv.orgWhen Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasterscs.LG updates on arXiv.orgPPDL: LLM-Based Flows as Probabilistic Programscs.LG updates on arXiv.orgDecoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Languagecs.LG updates on arXiv.orgDisentangling 3D Modeling from Spatial Reasoningcs.LG updates on arXiv.orgMarginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Modelscs.LG updates on arXiv.orgPRISM: Priority-aware Rubric Internalization via Structured Multimodal Data Synthesiscs.LG updates on arXiv.orgBeyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuningcs.LG updates on arXiv.orgBeyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuningcs.LG updates on arXiv.orgAn Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language Goalscs.LG updates on arXiv.orgEvaluating Machine Learning Models for Post-Wildfire Debris-Flow Predictioncs.LG updates on arXiv.orgRectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEGcs.LG updates on arXiv.orgQEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decodingcs.LG updates on arXiv.orgDG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accountingcs.LG updates on arXiv.orgQuantum-Structured World Models (QSWMs) for Predictive Latent Dynamicscs.LG updates on arXiv.orgSpectral Distillation: From Nonlinear Dynamics to Linear State-Space Modelscs.LG updates on arXiv.orgPerturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samplescs.LG updates on arXiv.orgIFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games
By Source
Feeds organized so you can skim by site.
Density
Sort
AB
Ai2 Blog
1d ago · 20 items
TutorMoments: Do AI tutors know when to help and when to hold back?
1d ago
TutorMoments is an open, replay-based evaluation framework that tests whether AI tutors can recognize when to support a student and when to hold back and encourage deeper reasoning.
Ai2 expands collaboration with Hugging Face to accelerate open science
2d ago
Ai2 is expanding its partnership with Hugging Face to give its growing portfolio of fully open models, datasets, benchmarks, and applications the storage, bandwidth, and integrations needed to reach more researchers and developers.
Tracing distinctive language in AI-written text
8d ago
Stony Brook researchers used our infini-gram engine to trace distinctive phrases in AI-generated writing back to existing sources, finding that top-selling self-published books on Amazon with substantial detected AI text overlap more heavil...
The OlmoEarth Platform: Geospatial inference at planetary scale
11d ago
How we built the OlmoEarth Platform to fine-tune geospatial models and run continent-scale satellite inference while managing massive data pipelines, distributed compute, and automatically recovering from failures at scale.
Who gets to understand AI?
15d ago
Why fully open models and research artifacts are essential to independent scrutiny, broader participation, and continued U.S. scientific leadership in AI.
What building Shippy taught us about building agents
26d ago
Building Shippy taught us that reliable agents depend less on the model itself than on deterministic tools, explicit guardrails, isolated infrastructure, and evaluations grounded in real-world workflows and live data.
MolmoAct 2 shows what open models can unlock for robotics
31d ago
Robotics engineer Binh Pham used MolmoAct 2 to build a voice-controlled robot that won South Park Commons’ embodied AI hackathon.
Modular LLMs at scale: how FlexOlmo is helping to pool national expertise without pooling sensitive data
37d ago
Danish Foundation Models is using FlexOlmo as the basis for FlexMoRE, a more efficient modular LLM architecture that lets institutions contribute specialized experts trained on sensitive or proprietary data without sharing that data—and run...
Which tokens does a hybrid model predict better?
44d ago
New token-level analyses of Olmo 3 and Olmo Hybrid show that hybrid models predict meaning-bearing, context-dependent tokens better than transformers, while transformers retain an edge on verbatim copying.
How Domyn and AISquared built on Ai2's open releases
51d ago
Domyn and AISquared show how Ai2’s open releases are helping AI labs build models for regulated industries, where transparency, provenance, licensing, and control are essential for customer trust and compliance.
MolmoMotion: Language-guided 3D motion forecasting
52d ago
olmo-eval: An evaluation workbench for the model development loop
57d ago
Building accessibility tools on a truly open foundation
79d ago
OlmoEarth v1.1: A more efficient family of models
81d ago
Introducing AIMIP: The AI weather and climate model intercomparison project
87d ago
Why Artificial Analysis uses Ai2's IFBench instruction-following eval
89d ago
EMO: Pretraining mixture of experts for emergent modularity
92d ago
Open by design: Ai2 brings fully open AI infrastructure online with NSF OMAI
93d ago
MolmoAct 2: An open foundation for robots that work in the real world
95d ago
What’s next for Ai2: A conversation with Interim CEO Peter Clark
99d ago
20 loaded
CL
cs.LG updates on arXiv.org
1d ago · 1320 items
MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification
1d ago
Abstract page for arXiv paper 2608.05196: MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification
When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters
1d ago
Abstract page for arXiv paper 2608.05207: When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters
PPDL: LLM-Based Flows as Probabilistic Programs
1d ago
Abstract page for arXiv paper 2608.05234: PPDL: LLM-Based Flows as Probabilistic Programs
Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language
1d ago
Abstract page for arXiv paper 2608.05238: Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language
Disentangling 3D Modeling from Spatial Reasoning
1d ago
Abstract page for arXiv paper 2608.05242: Disentangling 3D Modeling from Spatial Reasoning
Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models
1d ago
Abstract page for arXiv paper 2608.05243: Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models
PRISM: Priority-aware Rubric Internalization via Structured Multimodal Data Synthesis
1d ago
Abstract page for arXiv paper 2608.05249: PRISM: Priority-aware Rubric Internalization via Structured Multimodal Data Synthesis
Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning
1d ago
Abstract page for arXiv paper 2608.05250: Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning
Beyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuning
1d ago
Abstract page for arXiv paper 2608.05253: Beyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuning
An Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language Goals
1d ago
Abstract page for arXiv paper 2608.05255: An Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language Goals
Evaluating Machine Learning Models for Post-Wildfire Debris-Flow Prediction
1d ago
Rectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEG
1d ago
QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding
1d ago
DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting
1d ago
Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics
1d ago
Spectral Distillation: From Nonlinear Dynamics to Linear State-Space Models
1d ago
Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples
1d ago
IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games
1d ago
Why the Third Axis Is Freedom
1d ago
EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents
1d ago
C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning
2d ago
On Hamming-Lipschitz Type Stability of the Subdominant (Minmax) Ultrametric: Theory and Simple Proofs
2d ago
A Trust-region Framework for Moment Estimation
2d ago
Learning to Resolve Neutron Resonances with Fully Convolutional Neural Networks
2d ago
Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation
2d ago
An Explainable LLM Agent Layer for Open-World Anomaly Detection in Oil Wells
2d ago
Tactus: Open-Vocabulary Object Recognition from Low-Cost Pressure Arrays
2d ago
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity
2d ago
Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs
2d ago
CAMP: A Cycle-Aware Multi-Scale Patch Mixer for Time Series Forecasting
2d ago
LaPrune: Controllable Differentiable Sparsity at Million Scale
2d ago
SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors
2d ago
Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms
2d ago
Spatiotemporal Graph Transformer for Traffic Intelligence in Edge Computing
2d ago
SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
2d ago
Out-Of-The-Loop Multi-Fidelity Bayesian Optimization
2d ago
LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling
2d ago
MINT: Tensor Decomposition on Stacked Recurrence Matrices for Time Series Data Mining
2d ago
Understanding Fault Tolerance of Adversarially Robust Pruned Models
2d ago
TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction and a Tabular Foundation Model
2d ago
Deep Divide-and-Reduce in Symbolic Regression
3d ago
Multimodal Auto-regressive Transformer Surrogate for Modeling Variable Operations and Quantifying Uncertainty in Geological Carbon Storage
3d ago
LLMs Can Annotate Attribution Graphs
3d ago
GeoID-PINN: Identifiability-Aware Regional Epidemic Inference with Geographic Coupling
3d ago
Verifier-Guided Model Discovery for Physical Dynamical Systems with Pretrained Symbolic Transformers
3d ago
CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study
3d ago
Sphere Retraction Normalizations
3d ago
Learning Molecular Representations from Cellular Phenotypes with Structure Preservation
3d ago
GLOBE: Trajectory-Aligned Gradient Matching with Structured SparseOptimization for Coreset Selection
3d ago
Output-Aware Rotation for INT2 KV-Cache Quantization
3d ago
PatTree: a novel approach for automated creation of multimodal, graph-based patient representations for medical classification tasks
3d ago
Measuring Explainer Stability via Attribution Separability
3d ago
NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory
3d ago
Can Training Logs Make Model Comparisons More Precise?
3d ago
Designing a Good Virtual Node: Addressable and Cardinality-Preserving Global Memory for Message Passing Architectures
3d ago
Neural Networks with Local Converging Inputs for Efficient Options Pricing Models
3d ago
Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment
3d ago
Topological Simplification in Predictive Coding Networks
3d ago
Wiring Beats Blending: What Transfers Between Transformer Sizes -- and What Doesn't
3d ago
NOMADD: Numerical Optimization of Models Adapting to Data Drift
3d ago
Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language Models
4d ago
Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark
4d ago
MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing
4d ago
Progressive$^2$: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression
4d ago
Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset
4d ago
Leak It: A Probabilistic Approach to Training-Data Extraction from Black-Box Language Models
4d ago
Response Magnitude as a Dominant Signal for Held-Out CRISPRi Perturbation Effect Prediction
4d ago
Inference-Time Policy Alignment for Fair Reinforcement Learning
4d ago
AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery
4d ago
A Physics-Chemistry-Informed Neural Network (PCINN) for Real-Time Spatial-ALD Coverage Prediction and Reliable Kinetics Inversion
4d ago
Verifier-Induced Support Reshaping in On-Policy Optimization
4d ago
Similarity-Aware Machine Unlearning
4d ago
Stabilized Best-of-$K$ Training for Neural Combinatorial Optimization
4d ago
Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning
4d ago
Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
4d ago
Neural operator learning for collision-aware trajectory planning of spacecraft swarms
4d ago
Ensemble of Unsupervised Deep Learning for Clustering Imbalanced Tabular Data
4d ago
Modeling Unknown Nonlocal PDE Systems via Flow Map Learning
4d ago
DSETA: A Dual-Stage Continual Learning Framework for Travel Time Prediction in Dynamic Traffic Environments
4d ago
Unleashing the Potential of Large Language Models: A Blueprint for Real-Time, Enterprise-Ready Deployments
4d ago
Topology-Aware Data Movement for Disaggregated GPU Inference
5d ago
Sensitivity Analysis of GRU, LSTM and Transformer Encoder in Classification of Automated Driving Systems
5d ago
Guarantees on Dynamical System Distinguishability for LLM Token Generation
5d ago
LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment
5d ago
Hierarchical Copula-Gumbel-Top-\texorpdfstring{$K$}{K} Routing: Two-Sided Dependence Control for Frozen Mixture-of-Experts at Fixed Per-Token Routing Laws
5d ago
LAWFUL: Law-Aligned Witness for Faithful Use of Latents
5d ago
MPP-GNN: Subject-Adaptive Community Detection for fMRI-Based Alzheimer's Disease Classification
5d ago
Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions
5d ago
SEDR-Seq2P: A Lightweight Dilated Residual Sequence-to-Point Network for Multi-Task Industrial NILM
5d ago
Predicting Steel Fatigue Life from Micrographs Using Physics-Informed Deep Learning
5d ago
Mitigating Class-Tail Undercoverage in Medical Vision-Language Models under Clinical Shift
5d ago
Flow Matching with Missing Data
5d ago
MMFGU: Multimodal Federated Graph Unlearning
5d ago
Mirror Learning
5d ago
TAGTorch: A PyTorch Library for Geometry, Topology, and Symmetry-Aware Machine Learning
5d ago
Feature Interaction Modeling for Physics-Informed Neural Networks and Neural Operators
5d ago
Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation
5d ago
Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations
5d ago
Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity
5d ago
An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks
5d ago
Recursive transformers for semiconductor thermo-mechanical reliability
8d ago
Regularizing modality contribution drift in multimodal continual learning
8d ago
DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series
8d ago
PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective
8d ago
Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding
8d ago
RLPF: Reinforcement Learning from Performance Feedback for Code Generation
8d ago
SDO: Structure-Aware Data Organization for Efficient LLM Post-Training
8d ago
Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision
8d ago
Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents
8d ago
The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models
8d ago
Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance
8d ago
TIER-MoE: Trust-Informed Expert Routing via Conditional Modality Risk for Multimodal Fusion in Biomedical Classification
8d ago
EvoCause: LLM-Guided Evolution of Causal Graphs for Root Cause Analysis
8d ago
THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model
8d ago
Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models
8d ago
ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution
8d ago
Modeling Decisions in Blockchain Analytics: A Leakage-Aware Evaluation of Tree-Based vs. Sequential Models
8d ago
Compression-Based Behavioral Similarity for Open-World Sybil Discovery on Ethereum
8d ago
Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
8d ago
The Convergence Behavior of Adam under Heavy-Tailed Noise
8d ago
Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning
9d ago
Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football
9d ago
Meta-Learned Reward Shaping for Reinforcement Learning from Human Feedback
9d ago
Data Fusion and Contrastive Alignment for Unconstrained IR Molecular Structure Elucidation
9d ago
Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models
9d ago
Dynamic Parameterization Is Not Dynamic Inference
9d ago
Weak-to-Strong On-Policy Distillation
9d ago
Between Gradient and Natural Gradient: A Continuum of LoRA Initializations
9d ago
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
9d ago
Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection
9d ago
FloDR: An invertible dimensionality reduction method based on a normalising flow
9d ago
Entity Resolution in Practice: Lessons from a Self-Serve Pipeline
9d ago
Learning Implicit Causal World Models from Multi-Agent Demonstrations
9d ago
RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning
9d ago
Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks
9d ago
MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts
9d ago
High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumption
9d ago
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
9d ago
ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling
9d ago
Q-Steer: Action-Value Guidance for Molecular Policy Optimization
9d ago
FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting
10d ago
Human Preference aligned Tabular Similarity
10d ago
Behavior-Driven Explainability
10d ago
Eliminating Propagation Delay: Attention-Based Spatial-Temporal Fusion Graph Convolution Network for Traffic Flow Prediction
10d ago
Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension
10d ago
GAUGE: Grading Agent-Built Financial Models Without a Golden Answer
10d ago
LLM as Forecasting Planner: Training-Free Text Conditioning for Time-Series Foundation Models
10d ago
Inverse RL Helps Align AI by Imitating Humans
10d ago
Multiclass Classification without Labels via Posterior Simplex Geometry
10d ago
Stable FP4 Training via Transposition-Invariant Block Quantization
10d ago
Generative Distributionally Robust Optimization
10d ago
Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning
10d ago
Conformal Cascade: Distribution-Free Accuracy Guarantees for Multi-Tier LLM Inference
10d ago
Lantern: Conflict-Aware Gradient Blending for Physics-Guided Diffusion Models in Calorimeter Simulation
10d ago
Score-Based Stabilization for Time-Dependent Problems
10d ago
Semantic Space Search Trajectory Networks
10d ago
Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning
10d ago
Interpretable GOHR Agents via Sparse Autoencoders
10d ago
Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility
10d ago
Accurate structural modeling of chemically diverse molecular interfaces with Vilya-2
10d ago
Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B
11d ago
CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
11d ago
CausalGate: Causal Importance Distillation for Transformer Module Pruning
11d ago
Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
11d ago
QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
11d ago
Learning to Access Computation: Accessibility Plasticity as a Principle of Adaptive Intelligence
11d ago
Hierarchical Grading in Large Language Models
11d ago
An Integrated Deep Learning and Statistical Framework for Whole-Network Gene--Environment Association with Leaf Vascular Architecture
11d ago
Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation
11d ago
DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning
11d ago
Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement
11d ago
CC-AOS: Cost- and Horizon-Conditioned Amortized Backward Induction for Finite-Horizon Optimal Stopping
11d ago
Predicting the Outcome of rTMS Depression Therapy using EEG Signals and CNN
11d ago
LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning
11d ago
Multimodal Surface EMG Hand Gesture Recognition Using Query-Based Transformers for Prosthetic Control
11d ago
What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation
11d ago
Optimizing Transformer Neural Network for Real-Time Outlier Detection on FPGAs
11d ago
FMOPF: Latent Flow Matching with Constraint-Aware Interaction Priors for AC Optimal Power Flow
11d ago
Multimodal Domain Generalization for Depression Detection: An Attention-Based BiLSTM Network with Domain-Adversarial Training
11d ago
Physically Verifiable Evidence and LLM-Based Reporting for Bearing Fault Diagnosis
11d ago
Cloud-Native Evaluation-as-a-Service: A Microservices Architecture for Scalable AI Monitoring with Conformal Guarantees
12d ago
On the Depth Scalability of Logic Gate Networks
12d ago
MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion
12d ago
Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions
12d ago
Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models
12d ago
Quasi-Monte Carlo Initialization for Meta-Reinforcement Learning
12d ago
Toward Goal-Agnostic Joint-Embedding Predictive Control of Partial Differential Equations
12d ago
Multi-Horizon Consistency as Geometry: When Latent Dynamics Contract, and When They Do Not
12d ago
Adjustment Speed as a Safety Constraint for Nonstationary Reinforcement Learning
12d ago
A Drift Stable Quantum Federated Learning for Intelligent Services
12d ago
Shallower ReLU Network Representations via Exact Linear Algebra
12d ago
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
12d ago
Physically Constrained Federated Additive Models for O-RAN SLA-Risk Prediction
12d ago
Neural Feature Governance: Extending Atom Prevalence
12d ago
Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration
12d ago
Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA
12d ago
CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecasting
12d ago
Learning What Matters: Supervising Sparse Attention Routing with Causal Evidence Sets
12d ago
An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning
12d ago
A Defense of the Quadratic Model
12d ago
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
15d ago
PhantomFill: When the Form Demands an Answer, Language Models Invent One
15d ago
The Active Ingredient in Muon's Grokking
15d ago
Scaling Closed-Loop Feature Channel Configuration with LLMs
15d ago
Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs
15d ago
Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
15d ago
Generative Bayesian Filtering for State Estimation
15d ago
Do Active SAE Feature Planes Carry More Holonomy? A Preregistered Reversal in Gemma
15d ago
Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement
15d ago
CLOE: Christoffel Loss Autoencoder for Anomaly Detection
15d ago
Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development
15d ago
Grounding Investor Views: Neural Predicates in the Black-Litterman Model
15d ago
A Graph Neural Network approach to zero-shot Digital Twins
15d ago
ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
15d ago
Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches
15d ago
Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling
15d ago
From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime
15d ago
HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws
15d ago
Improving Access to Essential Medicines via Decision-Aware Machine Learning
15d ago
When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion
15d ago
Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
16d ago
Bayesian Wind Tunnels for Model Selection
16d ago
CruiseBench: A Real-Flight-Aligned N-CMAPSS Benchmark for Engine RUL Prediction
16d ago
Air Quality Arena: A Large-Scale Multi-Region Ground Monitoring Dataset and Benchmark for Air Quality Forecasting with Time-Series Foundation Models
16d ago
Challenges of Explainability in Continual Learning for Time Series Forecasting
16d ago
SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning
16d ago
STN-TGAT: Top-K Portfolio Construction via Prior-Guided Graph Attention with Learnable Soft-Threshold Sparsification
16d ago
Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance
16d ago
Scale-Aware Learning of Chaotic Dynamics on Unstructured Meshes via Binned Spectral Losses
16d ago
Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation
16d ago
The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory
16d ago
LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning
16d ago
Predicting Groundwater Arsenic Concentrations Using Graph Neural Networks
16d ago
Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks
16d ago
Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning
16d ago
From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation
16d ago
Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning
16d ago
Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models
16d ago
Predictive single cell foundation model for gene regulation and aging with privacy-preserving tabular learning
16d ago
When Does Consensus Beat Voting? A Critical Analysis of Statistical Label Fusion in Medical Image Segmentation
16d ago
FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration
17d ago
Beyond Output-Space Calibration: Spectral Evidence Bundling for Selective Reliability Estimation in Time-Series Classification
17d ago
Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models
17d ago
ALAS: Additive Learnable Alpha-Stable Kernels for Flexible Bayesian Optimization
17d ago
FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images
17d ago
Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression
17d ago
Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring
17d ago
Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority
17d ago
BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop
17d ago
Multi-Timescale Latent-Action DRL for Joint Optimization in Edge-Cloud Networks
17d ago
Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios
17d ago
SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions
17d ago
Dual-domain fused LSTM modeling for efficient time-dependent reliability analysis
17d ago
Reliability Scales Inversely: Bigger Models Compound Mistakes Faster via a Hidden Auto-Regressive Risk Regime
17d ago
One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context
17d ago
Uncertainty Quantification for AI-Driven Crash Simulation Surrogates: A Comparative Study of Monte Carlo Dropout and Deep Ensemble on Open-Source Bumper Beam Benchmark
17d ago
On the Limits of Support-Preserving Alignment and Bounded Filtering
17d ago
A Better Start for Language Models: Domain-Conditional Position Offsets
17d ago
TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue
17d ago
The Information Shadow: Measuring Structural Limits on What Language Models Can Learn
17d ago
Reinforcement Learning-Guided NSGA-II Enhanced with Gray Relational Coefficient for Multi-Objective Optimization: Application to NASDAQ Portfolio Optimization
18d ago
DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
18d ago
Fully-sensorized smart-eyewear platform for on-device Machine Learning
18d ago
LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats
18d ago
Operator-Aware Mixed-Precision Tolerance Calibration for Tensor Kernels
18d ago
RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce
18d ago
Orthogonal Gradient Constraints Shape Noisy-Label Memorization Dynamics
18d ago
From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language
18d ago
Token-Level Cross-Modal Transformer with Contrastive Multi-Task Learning for Breast Cancer Subtype Classification and Survival Prediction
18d ago
HantaWatch: Federated Learning for Hantavirus Genomic Surveillance
18d ago
OpenMHC: Accelerating the Science of Wearable Foundation Models
18d ago
The Failures of Marginal Influence-Based Attribution Methods for Global Time Series Explanations
18d ago
Quantizing Recursive Reasoning Models
18d ago
Diffusion-corrected Autoregressive Fourier Neural Operator for Droplet Evolution Prediction
18d ago
BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges
18d ago
Normalized Rewards for Preference Optimization
18d ago
KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?
18d ago
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
18d ago
RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants
18d ago
CIGPO: Contextual Information-Gain Policy Optimization for Multi-Turn Evidence-Reading LLM Agents
18d ago
Structure of the Circular-Dyadic Convolution Error
19d ago
Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling
19d ago
A Transportable Threshold-Based Framework for Interpretable Classification of Medical Data
19d ago
Regularity-Aware Stochastic MGDA with Adaptive Conflict-Avoidant Update Direction Control
19d ago
AI Trading: Evaluating Large Language Models for Technical Market Analysis
19d ago
qZACH-ViT: Quantization-Aware Intrinsic Explanations with Recursive Attribution-Stabilized Optimization
19d ago
From hyperplanes to hyperellipsoids: characterizing the inherent interpretability of linear and single-qubit mixed-state binary classification models
19d ago
Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths
19d ago
Who Became Financially Vulnerable After COVID-19? A Population-Level Machine Learning Analysis Using MEPS Data
19d ago
LLM4EHR: Aligning Clinical Time Series with Medical Event Sequences via Large Language Models
19d ago
Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention
19d ago
Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers
19d ago
Robust Peak-cost Constrained Reinforcement Learning
19d ago
ADS-C: Antidistillation Sampling for Classification
19d ago
Deep Learning Approaches for Sleep Apnea Classification from Polysomnographic EEG Signals
19d ago
Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations
19d ago
Diffusion models recover accurate mixture weights despite score function insensitivity
19d ago
An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism
19d ago
Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching
19d ago
Recursive Harness Self-Improvement
19d ago
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
22d ago
CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models
22d ago
Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence
22d ago
Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees
22d ago
QFireNet: A Quantum-Enhanced U-Net for Wildfire Segmentation from Sentinel-2 Imagery
22d ago
Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
22d ago
How Much of a 10-K Matters? Aggregation-Dependent Value of Full-Text versus Risk-Factor Sentiment
22d ago
Low-Latency Relay Selection in NR-V2X Vehicular Communications via Graph Isomorphism Networks with Edge Features
22d ago
RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences
22d ago
Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape
22d ago
A Temporal Machine Learning-Based Time-to-Event Model for Predicting ALS Progression and Healthcare Utilization
22d ago
TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories
22d ago
Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning
22d ago
Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games
22d ago
Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks
22d ago
LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks
22d ago
MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion
22d ago
Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist
22d ago
Lyapunov Guidance: A Unified Framework for Stabilizing Generative Flows
22d ago
NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis
22d ago
Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks
23d ago
Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning
23d ago
Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges
23d ago
What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry
23d ago
Targeted Recovery of Weight-Space Mechanisms From Neural Networks
23d ago
Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
23d ago
TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling
23d ago
Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing
23d ago
STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting
23d ago
A Hybrid Mamba for Audio-Visual Navigation
23d ago
CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion
23d ago
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
23d ago
HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtration
23d ago
SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy
23d ago
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
23d ago
EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting
23d ago
Reassessing Muon for Matrix Factorization
23d ago
Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners
23d ago
Tabular Foundation Models for Discrete Choice Estimation
23d ago
Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting
23d ago
OmniPMNet: Bridging discrete and gridded PM10 forecasts via omni-query neural processes
24d ago
Semidirect Fourier Delta Attention: Phase-Controlled Delta Memory with Constructive Chunk-WY Kernels
24d ago
Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
24d ago
Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding
24d ago
Mirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection
24d ago
Mathematics of Data Science
24d ago
CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA
24d ago
How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit
24d ago
BattVAE-GP: Generative Modeling of Long-Horizon Battery Degradation with Uncertainty Quantification
24d ago
Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite
24d ago
Scale-Aware Attention for Scarce Neural Data: An RG-Flow Transformer on Sleep-EDF EEG
24d ago
Scalable Optimal Transport Algorithm for Network Alignment
24d ago
When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary
24d ago
Graph-Constrained Policy Learning for Extreme Clinical Code Prediction
24d ago
Exact and Certified Data Shapley for Weighted k-Nearest-Neighbor Regression and Soft-Label Prediction
24d ago
Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle
24d ago
Evaluating Reliability in Machine Learning Models for Early Chronic Kidney Disease Prediction: A Systematic Review of Data Leakage and Predictor Stability
24d ago
LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving
24d ago
Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse
24d ago
Self-Evolving In-Context Learning for Direct Pilot-to-Beamformer Design in MU-MISO Systems
24d ago
Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
25d ago
Position: Every Ground Truth is a Human Construction, not an Objective Truth
25d ago
AuditWeave: A Tamper-Evident, Auditor-Navigable Evidence Layer for AI-Assisted and Data-Transformation Workflows
25d ago
Ablation, Statistical Inference, and Validation for KV-Cache Compression
25d ago
SciML in the Wild: A Diagnostic Study of When Structural Priors Help and When They Hurt
25d ago
MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference
25d ago
Prioritizing Search Space Regions in the Low Autocorrelation Binary Sequences Problem
25d ago
What Context Does a Coding Agent Actually Need to Act?
25d ago
Reference-Based Distillation Detection in LLMs
25d ago
Depth-Entropy Guided Sampling for Training-Free LLM Reasoning
25d ago
Low-Rank Attention Residuals
25d ago
FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift
25d ago
Mitigating Early Training Collapse in CTR Models
25d ago
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
25d ago
Quantum-Inspired Contextual Learning for Sparse-Ring Fraud Detection in Dynamic Transaction Graphs
25d ago
Manifold Constrained Tabular Deep Neural Networks
25d ago
EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
25d ago
ERP Data Provisioning Financial Control Testing
25d ago
Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls
25d ago
Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels
25d ago
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
26d ago
iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis
26d ago
Signed Symmetric Quantization for Few-Bit Integers
26d ago
Sticky Routing: Training MoE Models for Memory-Efficient Inference
26d ago
Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
26d ago
Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement
26d ago
LieBN: Batch Normalization over Lie Groups
26d ago
HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
26d ago
DaDaDa: A Dataset for Data Pricing in Data Marketplaces
26d ago
Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices
26d ago
Adaptive Bayes exactly tracks information over intrinsic time
26d ago
Prompt-Driven Exploration
26d ago
How are linear representations learned? Exact solutions to the dynamics of abstraction
26d ago
Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal
26d ago
Pattern-Aware Graph Neural Networks for Handling Missing Data
26d ago
A Machine Learning Surrogate for Component Criticality Ranking in Interdependent Power-Communication Networks
26d ago
SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions
26d ago
BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving
26d ago
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
26d ago
Training, Reading, and Editing Legible Transformers
26d ago
Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
29d ago
Who Gets Missed in the Tail? Thresholded Subgroup Underdiagnosis in Long-Tailed Chest X-ray Classification
29d ago
LLT: Local Linear Transformer for PDE Operator Learning
29d ago
ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning
29d ago
Omni-Sleep: A Sleep Foundation Model via Hierarchical Contrastive Learning of CNS--ANS Dynamic
29d ago
Uncertainty-gated selection for block-sparse attention
29d ago
SHIFT: Survival Prediction from Incomplete and Heterogeneous Genomic Data
29d ago
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
29d ago
Architecture Generalization with MetaNCA
29d ago
LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks
29d ago
Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation
29d ago
A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents
29d ago
Image classification via a quantum-inspired strategy involving a mixture of experts
29d ago
The Importance of Encoder Choice:A Tabular-Image Study
29d ago
Scalable and Trustworthy Earth Observation Foundation Models
29d ago
Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives
29d ago
Unlocking Temporal Generalization in Hamiltonian Video Dynamics Models
29d ago
Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms
29d ago
Graph-Regularized Deep Learning for EEG-Based Emotion Recognition with Psychologically-Grounded Label Structure
29d ago
A law of robustness for two-layer neural networks with arbitrary weights
29d ago
TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation
30d ago
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
30d ago
NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts
30d ago
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
30d ago
Deep Reinforcement Learning for Reliability Based Bi-Objective Portfolio Optimization
30d ago
STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting
30d ago
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
30d ago
Inertia-1: An Open Exploration of Wearable Motion Foundation Models
30d ago
Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention
30d ago
LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting
30d ago
Open-Ended Scenario Reasoning for Specialist Model Adaptation
30d ago
Reward Valuation in Vision Language Models: Causal Mechanisms Underlying Anhedonia
30d ago
Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking
30d ago
STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning
30d ago
When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models
30d ago
Does Demand Response Increase Vulnerability to Cyber Attacks by Adversarial Data Modifications?
30d ago
When Do Geometric Algebra Layers Beat Scalarization? A Controlled Study on SO(3)-Equivariant Vector Laws
30d ago
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
30d ago
UASPL: Uncertainty-Aware Self-Paced Learning with Evidential Neural Networks
30d ago
At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics
30d ago
Statistically Meaningful Geometry and Gauge Symmetry Breaking: A Geometric Foundation for Scientific Discovery and Intelligence Emergence
31d ago
Design-CP: Context Parallelism for Design of Protein Nanoparticles
31d ago
Geometry-Aware Infrastructure-Anchored Denoiser for UWB Sensing and Work-Zone Reconstruction
31d ago
The Granularity Paradox: How Temporal Disaggregation Inflates In-Sample Fit and Compounds Out-of-Sample Error
31d ago
Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates
31d ago
Empirical Minimal-Realisation Compression of Deep Neural Networks via Controllability-Observability Tests
31d ago
Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning
31d ago
AdaStop: Cost-Aware Early Stopping for DNN Test Selection
31d ago
Learnable Weighting of Intra-Attribute Distances for Categorical Data Clustering with Nominal and Ordinal Attributes
31d ago
Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy
31d ago
Parameter-Free Encoders Remain Viable for RDB Foundation Models
31d ago
InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs
31d ago
PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates
31d ago
$\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse
31d ago
Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation
31d ago
Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids
31d ago
EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation
31d ago
SafeImpute: Reliable Clinical Data Imputation via Conformal Selection
31d ago
A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models
31d ago
Safe Bayesian Optimization with Counterfactual Policies
31d ago
Auditing the Audit: Five Failure Modes in Benchmark-Validity Audits
32d ago
Evaluating Time Series Foundation Models for Electricity Price Forecasting: Contamination Risk, Distributional Shifts, and Covariate Dependence
32d ago
QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting
32d ago
GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech
32d ago
Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data
32d ago
Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting
32d ago
A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction
32d ago
LiNO: Lifting based multiresolution neural operator
32d ago
Weighted Conformal Prediction for Lab-to-Track Thermal Transfer in EV Motorsport Powertrains
32d ago
Out-of-Distribution Generalization of Risk Aversion in Language Models
32d ago
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
32d ago
Induction Heads Interpolate N-Grams
32d ago
Training Hybrid Block Diffusion Language Models with Partial Bidirectionality
32d ago
Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
32d ago
On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
32d ago
Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data
32d ago
Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading
32d ago
Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models
32d ago
Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs
32d ago
Dynamic Regret for Non-Stationary Linear Bandits via Misspecification Reductions
32d ago
Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
36d ago
I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals
36d ago
Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery
36d ago
Domain Knowledge Based Temporal-Spatial Graph Convolution Network for ECG Recognition
36d ago
Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions
36d ago
IonSense-QKG: A Quantum-Readiness Metadata Framework for Lithium-Ion Battery Dataset Discovery
36d ago
A Novel Machine Learning Approach for Central Nervous System Tumor Classification from DNA Methylation
36d ago
From Approximation to Emergence: A Theory of Deep Learning
36d ago
Black-Box Inference of LLM Architectural Properties with Restrictive API Access
36d ago
Multi-modal Rail Crossing Safety Analysis
36d ago
How Should Transformers Encode Numeric Values in Electronic Health Records?
36d ago
NeuroBridge: Bridging Multi-Task MRI Knowledge for Neurodegenerative Disease Diagnosis
36d ago
Spin-Weighted Spherical Harmonics Enable Complete and Scalable $\mathrm{E}(3)$-Equivariant Networks
36d ago
The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning
36d ago
Conditional Inference Trees and Forests for Feature Selection
36d ago
On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain
36d ago
Geometry-Aware R-Structured Kolmogorov-Arnold Networks
36d ago
Token Geometry
36d ago
Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
36d ago
How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size
36d ago
Representation as a Bottleneck for Mechanistic Interpretability: The Manifestation Unit Protocol
37d ago
SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling
37d ago
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
37d ago
A Filtered Mixture-of-Generators for Fully Synthetic Survival Training
37d ago
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
37d ago
EVOTS: Evolutionary Transformer Search for Time Series Forecasting
37d ago
FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts
37d ago
Verifiable Rewards for Calibrated Probabilistic Forecasting
37d ago
Scaling Up Thermodynamic AI Models
37d ago
TallyTrain: Communication-Efficient Federated Distillation
37d ago
Play Like Champions: Counterfactual Feedback Generation in Latent Space
37d ago
TRIE: An Evaluation Framework for Stochastic PDE Surrogates
37d ago
StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting
37d ago
Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts
37d ago
Distributionally Robust Linear Regression With Block Lewis Weights
37d ago
Learning dynamical systems from noisy data with Weak-form Kernel Ridge Regression
37d ago
Validating Causal Abstraction Metrics on Simulated Complex Systems
37d ago
Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning
37d ago
Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds
37d ago
Understanding Guest Preferences and Optimizing Two-sided Marketplaces: Airbnb as an Example
37d ago
Joint discovery of governing partial differential equations from multi-source datasets by competitive optimization
38d ago
Accelerometry-Derived Digital Biomarkers for Cardiometabolic Risk: A Population-Representative Tabular Benchmark with Uncertainty Quantification
38d ago
From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
38d ago
Why Do Few-Step Text Latents Fail When Image Latents Work? Non-Commitment at Sharp Categorical Readouts
38d ago
Hierarchical Global Attention (HGA)
38d ago
ReactionAtlas: Ab origine exploration of chemical reaction networks with machine learning
38d ago
Revocable Learned State via Process Sidecars
38d ago
Predictable GRPO: A Closed-Form Model of Training Dynamics
38d ago
Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization
38d ago
Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias
38d ago
Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization
38d ago
A Stationary-Distribution Theory for Triplet-Based Plateau Search in Random Forest Ensemble-Size Selection
38d ago
A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels
38d ago
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
38d ago
Personalizing Marketplace Policies with Competing Objectives and Constrained Experiments: Evidence from a Job Marketplace
38d ago
Quality-Aware Modulation for Diffusion Transformers
38d ago
Physics-informed Conditional Normalizing Flows for Angles-only Cislunar Orbit Determination
38d ago
Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
38d ago
Estimating Supply Incrementality in Two-sided Marketplaces: A Causal Machine Learning Approach
38d ago
Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction
38d ago
Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models
39d ago
On the Necessity of a Liquid Substrate for Mesh Intelligence
39d ago
Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy
39d ago
Learning to Distributedly Estimate under Partially Known Dynamics: A Covariance-Agnostic Neural Kalman Consensus Filter
39d ago
S-GAI: Spectral Geometry-Aware Initialization for Sigmoidal MLPs -- From Dataset Geometry to Network Weights
39d ago
scKDGM: KAN-guided Dynamic Graph Masked Learning for Single-Cell RNA-seq Clustering
39d ago
Counterfactual Residual Data Augmentation for Regression
39d ago
Singular Learning and Occam's Razor in Deep Monomial Networks
39d ago
An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations
39d ago
Modelling Emotional Memory in Children with Tensor Networks
39d ago
A Trainable-by-Parts Operator Learning Framework: Bridging DeepONet and Karhunen-Loeve Expansions for Large-Scale Applications
39d ago
A Gravitational Interpretation of Fine-Tuning Reversion
39d ago
NIVA: A Multimodal Foundation Model for Actionable Earth System Intelligence
39d ago
Improving Coherence in Hierarchical Time Series Forecasting using Structured Temporal Fusion
39d ago
Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings
39d ago
Replica Symmetry Breaking and Algorithmic Thresholds in Empirical Risk Minimization under Multi-Index Model
39d ago
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
39d ago
Randomized Exploration for Linear Bandits via Absolute Perturbations
39d ago
Improving Patient Subtyping on Longitudinal Data using Representations from Mamba-based Architecture
39d ago
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling
39d ago
OverFlowLight: Real-Time Gridlock Prevention and Traffic Signal Optimization for Urban Intersections
40d ago
RANSAC Scoring Done Right
40d ago
Unified Zero-Shot Time Series Forecasting: A Darts Foundation
40d ago
PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding
40d ago
Learning in Markovian bandits with non-observable states and constrained decision epochs
40d ago
Prism Transformer: Progressive Head Schedules for Hierarchical Attention Processing
40d ago
Operator Learning for Cubic Nonlinear Schr\"odinger Equation on Periodic Domains
40d ago
The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
40d ago
Boundary condition fidelity for bottom-hole pressure and CO2 plume prediction in geological carbon storage
40d ago
Productionized Fairness Measurement Under Privacy Constraints
40d ago
Quantum Generative Diffusion Model for Real-World Time Series
40d ago
hia-gat: A Heterogeneous Interaction-Aware Graph Attention Network For Frame-Level Traffic Conflict Risk Prediction On Freeways
40d ago
PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration
40d ago
Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF
40d ago
Global Explanations for Multivariate Time Series Forecasting Models via $K$-Order Markov Approximations
40d ago
Training Observable Control Policies to Expose Agent State Through Actions
40d ago
COOPA: A Modular LLM Agent Architecture for Operations Research Problems
40d ago
FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks
40d ago
HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models
40d ago
Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis
40d ago
Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics
43d ago
\chisao{}: A GPU-Native Parallel Optimizer for Multimodal Black-Box Functions via Convergence-Anticonvergence Oscillation
43d ago
Implementation of reinforcement learning in chemical reaction networks: application to phototaxis as curiosity-driven exploration
43d ago
Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis
43d ago
KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction
43d ago
Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations
43d ago
Clue-Guided Money Laundering Group Discovery
43d ago
Federated Hash Projected Latent Factor Learning
43d ago
Statistical and Structural Approaches to Algorithmic Fairness
43d ago
Topology-Informed Neural Networks for Flood Detection in Optical and Synthetic Aperture Radar Imagery
43d ago
A General Framework for Learning Algebraic Properties from Cayley Graphs using Graph Neural Networks
43d ago
Fast LeWorldModel
43d ago
Dataset Usage Inference without Shadow Models or Held-out Data
43d ago
Equivariance and Augmentation for Bayesian Neural Networks
43d ago
SSM Adapters via Hankel Reduced-order Modeling: Injection Site Determines Task Suitability in Long-Context Fine-Tuning
43d ago
The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
43d ago
High-Probability PL-SGD with Markovian Noise: Optimal Mixing and Tail Dependence
43d ago
EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning
43d ago
Mesh-RL: Coupled subgrid reinforcement learning
43d ago
EMA-FS: Accelerating GBDT Training via Gain-Informed Feature Screening
43d ago
Dense Supervision Is Not Enough: The Readout Blind Spot in Looped Language Models
44d ago
From Meta Idea to Advanced Mathematical Discovery -- Human-AI Co-Discovery of Sign-Embedding Quantum Algorithms
44d ago
On-Device Neural Architecture Search
44d ago
LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning
44d ago
A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis
44d ago
When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models
44d ago
Conformal Orbit-Valid Trust Horizons for Equivariant World Models
44d ago
Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources
44d ago
Holographic Memory for Zero-Shot Compositional Reasoning in Knowledge Graphs: A Mechanistic Study of Where and Why It Fails
44d ago
MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios
44d ago
How Complexity Contributes to Learning Opacity in Machine Learning
44d ago
Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity
44d ago
Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series
44d ago
Convex--Concave Quadratic Spectral Filtering for Graph Neural Networks
44d ago
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems
44d ago
Reliable Conformal Prediction for Ordinal Classification Using the Ranked Probability Score
44d ago
Enhancing Clinician Decision-Making via Uncertainty-Aware Multi-Expert Fusion for Stroke Rehabilitation
44d ago
Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models
44d ago
Evidence for feature-specific error correction in LLMs
44d ago
Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach
44d ago
Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search
45d ago
Weight-Space Geometry of Offline Reasoning Training
45d ago
A Survey on Federated Causal Discovery and Inference
45d ago
Low-power analogue neural networks with trainable nonlinear connections for continuous control
45d ago
Synergizing Physically Constrained MCMC and Chemical-Informed Gaussian Processes for Reaction Network Discovery
45d ago
Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios
45d ago
One Ruler: A Same-Hands Re-Evaluation of Bivariate Causal Direction on Tuebingen, with a Parameter-Free Compression Baseline
45d ago
Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction
45d ago
Reconstructing GRACE Terrestrial Water Storage with Spatio-Temporal Graph Neural Networks: An Application to South America
45d ago
The Degeneracy Distillery
45d ago
Machine Learning Modeling for Real-Time Melt Pool Monitoring in Laser Powder Bed Fusion Additive Manufacturing: A Hybrid Approach
45d ago
Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning
45d ago
Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications
45d ago
Exact Schur-Sylvester Dimensionality Reductions for Non-Smooth Stochastic Complexity and Manifold Sampling
45d ago
Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data
45d ago
MGI: Member vs Generated Inference
45d ago
GRACE: Gated Refinement for Accurate Causal Edge Discovery in High-Dimensional Time Series
45d ago
ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation
45d ago
Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI
45d ago
Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate
45d ago
Towards CSI-Native Foundation Models: A Channel-Adaptive Roadmap for 6G
46d ago
NeuroShield: A Device-Agnostic Foundation Model for EEG Authentication
46d ago
Massive Activations Are Architecturally Robust: A Controlled Scratch/Commitment Residual Stream Test
46d ago
CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks
46d ago
Evidential Fusion Network for Multimodal Survival Prediction under Missing Modalities
46d ago
ELADO: Elliptic PDE Assessment Datasets for Operator Learning
46d ago
B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet
46d ago
CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes
46d ago
Evolutionary Discovery of Developmental Reward Schedules in Deep Reinforcement Learning
46d ago
Machine Learning Classification of Cryopathy Syndromes: A Comprehensive Comparative Study
46d ago
Understanding Latent Flow Models for Tabular Data Synthesis: Targets, Paths, and Sampling
46d ago
Temporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals
46d ago
MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction
46d ago
Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels
46d ago
Short-Term Electricity Demand Forecasting for New England Using a Hybrid Transformer-XGBoost Framework with Weather, Calendar, and COVID-19 Indicators
46d ago
$\Omega$: Operator-based Mixture Ensemble for Generative Assimilation
46d ago
Hierarchical Pooling for Sheaf Neural Networks
46d ago
Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study
46d ago
Learning through Internalization
46d ago
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention
46d ago
Computational Identifiability
50d ago
When to Trust, How to Distill: Multi-Foundation Model Guidance for Lightweight, Robust Scientific Time Series Forecasting
50d ago
Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM Inference
50d ago
Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
50d ago
Information Lattice Learning as Probabilistic Graphical Model Structure Learning
50d ago
Weibull Weight-Scale Parameter Evolution under AdamW Training Dynamics
50d ago
Zero-Inflated Gaussian Distributions Enable Parameter-Space Sparsity in Estimation-of-Distribution Algorithms
50d ago
Human-like autonomy emerges from self-play and a pinch of human data
50d ago
ProMUSE: Progressive Multi-modal Uncertainty-guided Staged Evidential Alzheimer Disease Classification
50d ago
cAPM: Continual AI-Assisted Pace-Mapping with Active Learning
50d ago
Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs
50d ago
Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations
50d ago
Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees
50d ago
Emyx: Fast and efficient all-atom protein generation
50d ago
A Hybrid GNN-FEM Framework for Phase-Field Fracture Simulation. Physics-Preserving Hybridization for Generalizable Surrogate Modeling
50d ago
How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural
50d ago
VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving
50d ago
Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models
50d ago
FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning
50d ago
Spectral DPPs via NEPv: A Scalable Continuous Relaxation of Determinantal MAP for Diversity-Aware Data Selection
50d ago
Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing
51d ago
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
51d ago
CODEBLOCK: Learning to Supervise Code at the Right Granularity
51d ago
Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS
51d ago
A Link between Shock-wave Theory and Symmetry-reduced Stochastic Gradient Descent for Artificial Neural Networks
51d ago
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
51d ago
Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds
51d ago
DRIFT: Refining Instruction Data via On-Policy Data Attribution
51d ago
TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning
51d ago
SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector
51d ago
Ghost Attractor Networks: Basin-Structured Dynamical Decoders for Closed-Loop Sequential Generation
51d ago
A Survey on Data-Driven Models for Soil Moisture Regression and Classification
51d ago
Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion
51d ago
ASTRA: A Scalable Next-Generation ATCO Training Simulator with Autonomous Simpilots
51d ago
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior
51d ago
Why SWAVE May Not Be All You Need:A Concept-Evolution Retrospective on Complex-Valued Recurrent Language Models
51d ago
Neural Network Implementation of the Renormalization Group for Fault Diagnosis with Class Imbalance
51d ago
Self-CTRL: Self-Consistency Training with Reinforcement Learning
51d ago
ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets
51d ago
Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting
51d ago
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
52d ago
Diagnosing and Repairing Shape-Prior Shortcuts in Long-Range Single-Shot Fringe Projection Profilometry
52d ago
Informative Missingness to Generate Irregular Clinical Time Series
52d ago
Models Take Notes at Prefill: KV Cache Can Be Editable and Composable
52d ago
The Critical Role of Model Selection in Causal Inference: A Comparative Analysis of Classification Models within the InferBERT Framework for Pharmacovigilance
52d ago
Probing, Fusion, and Trustworthiness: A Systematic Evaluation of Foundation Model Representations for Multimodal Cancer Analysis
52d ago
MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs
52d ago
Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks
52d ago
Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations
52d ago
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
52d ago
Finsler Geometry, Graph Neural Networks, and You
52d ago
Constrained Diffusion Models with Primal-Dual Inference
52d ago
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
52d ago
Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization
52d ago
Rift: A Conflict Signature for Deception in Language Models
52d ago
Uncertainty Quantification of Engineering Structures by Polynomial Chaos Expansion and Multivariate Active Learning
52d ago
Rethinking Groups in Critic-Free RLVR
52d ago
ProCUA-SFT Technical Report
52d ago
Decision-Driven Geosteering Under Uncertainty: A Unified Framework for Sequential Decision Optimization
52d ago
Counterfactual Optimization of Baseball Pitch Sequences and Estimation of Its Impact on Season-Level Statistics
52d ago
QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
53d ago
GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness
53d ago
{\alpha}-Fair Insurance Pricing: A Fairness Continuum
53d ago
GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning
53d ago
Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts
53d ago
Separable Neural Architectures as Physical World Models: from Mathematical Theory to Applications
53d ago
Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation
53d ago
A Comparative Study of Graph Neural Network Layer Selection for Interaction Modelling in Driving Trajectory Prediction
53d ago
Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning
53d ago
Benchmarking Instance-Dependent Label Noise with Controlled Corruptions
53d ago
Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning
53d ago
FastMix: Fast Data Mixture Optimization via Gradient Descent
53d ago
Rational Sparse Autoencoder
53d ago
Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders
53d ago
How Should World Models Be Evaluated? A Decision-Making-Centric Position
53d ago
Transformers Learn the Mestre-Nagao Heuristic
53d ago
Temporal Difference Learning for Diffusion Models
53d ago
Physics-conforming Latent Twins
53d ago
Size Doesn't Matter: Cosine-Scored Sparse Autoencoders
53d ago
Machine Learning and the Random Walk Puzzle: Forecasting the CAD/USD Exchange Rate with Expanding Window Evaluation and SHAP Interpretability
53d ago
Can Editing 1 Neuron Fix Repetition Loops in LLMs?
54d ago
Efficient On-Device Diffusion LLM Inference with Mobile NPU
54d ago
High-Frequency Pricing at Scale for E-Commerce
54d ago
A fully GPU-based workflow for building physics emulators of hypersonic flows
54d ago
FedSPC: Shared Parameter Correction for Personalized Federated Learning
54d ago
The Weight Norm Sets the Grokking Timescale: A Causal Delay Law
54d ago
D2H-AD: A Hybrid Model Utilizing Hyperdimensional Computing for Advanced Anomaly Detection
54d ago
Beyond LoRA: Is Sparsity-Induced Adaptation Better?
54d ago
Diffusion Policy Optimization without Drifting Apart
54d ago
Neural Variability Enhances Artificial Network Robustness
54d ago
Neural Slack Variables for Shape Constraints
54d ago
Uncertainty Estimation and Generalization Bounds for Modern Deep Learning
54d ago
Attention-Based Estimation of the Individual Treatment Benefit Probability under Dose Variation
54d ago
A Stationarity-and-Coupling Criterion for Training-Free Time-Lagged Spectral Embeddings of Multivariate Time Series
54d ago
SuperThoughts: Reasoning Tokens in Superposition
54d ago
Muon$^p$: Muon with Fractional Spectral Powers
54d ago
Natively Unlearnable Large Language Models
54d ago
A Longitudinal Attribute-Conditioned Neural Network for Modeling Health-State Transition Probabilities in Temporally Irregular Data: The LANTERN Framework
54d ago
Gefen: Optimized Stochastic Optimizer
54d ago
SpikF-GO: Spiking Fourier Graph Operators for Multivariate Time Series Forecasting
54d ago
Restless bandits with imperfect binary feedback: PCL-indexability analysis and computation
58d ago
To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending
58d ago
Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
58d ago
Few-Shot Resampling for Scalable Statistically-Sound Data Mining
58d ago
ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation
58d ago
Physics-informed generative AI for semiconductor manufacturing: Enforcing hard physical constraints in generative models by construction
58d ago
Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems
58d ago
Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization
58d ago
Loss Landscape Diagnosis for Gradient-Based Gray-Scott System Inversion: Disentangling the Roles of PINN Components
58d ago
PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
58d ago
Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models
58d ago
A prior-free blind detection of information leakage from model predictions
58d ago
LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data
58d ago
Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation
58d ago
Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data
58d ago
RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways
58d ago
Least-Action-Guided Diffusion for Physical Extrapolation
58d ago
FreeBridge: Variational Schr\"odinger Bridges for Cellular Transition Dynamics
58d ago
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
58d ago
Learning from almost nothing: How neural networks survive heavy input corruption
58d ago
Mechanistic Analysis of Alignment Algorithms in Language Models
59d ago
SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning
59d ago
Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows
59d ago
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding
59d ago
Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages
59d ago
Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
59d ago
Blurry Window Attention
59d ago
From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents
59d ago
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
59d ago
LLM-as-a-Discriminator: When Synthetic Tables Still Look Real
59d ago
Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning
59d ago
SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs
59d ago
QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning
59d ago
PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks
59d ago
Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning
59d ago
Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection
59d ago
Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
59d ago
Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs
59d ago
Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM Wikis
59d ago
FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses
59d ago
Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark
60d ago
MedicalRec: Medical recommender system for image classification without retraining
60d ago
SPIN: Decentralized Swarm Control via Tensorized Policy Coordination
60d ago
Boundary Variance Inflation Causes Acquisition Bias in Gaussian Processes
60d ago
Emergence via Phase Transitions: Mechanism Landscapes and Universal Convergence Across Complex Systems
60d ago
STARIXNet: Multivariate and Multi-attribute Deep Learning Approach to Real-Time Resource Allocation in Cloud Platforms
60d ago
TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation
60d ago
Enabling KV Caching of Shared Prefix for Diffusion Language Models
60d ago
When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery
60d ago
MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport
60d ago
Training-Inference Kernel Contracts: Bounding Divergence in Post-Training and Deployment
60d ago
Customer Churn Prediction on Structured Data Using FT-Transformer and Stacking Ensembles
60d ago
Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks
60d ago
From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUs
60d ago
The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers
60d ago
Optimality of Sequential Filtering Under Independent Cost and Selectivity Models
60d ago
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
60d ago
UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning
60d ago
Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates
60d ago
Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them
60d ago
Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios
61d ago
FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models
61d ago
Multi-Scale Feature Attention Network for Polymer Classification using THz Dual-Comb Spectroscopy
61d ago
MacArena: Benchmarking Computer Use Agents on an Online macOS Environment
61d ago
WAV: Multi-Resolution Block Residual Routing for Deep Decoder-Only Transformers
61d ago
Are you sure? A Comprehensive and Comprehensible Survey of Uncertainty Quantification in Symbolic Regression
61d ago
Generative Models Erode Human Temporal Learning Through Market Selection
61d ago
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
61d ago
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
61d ago
Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory
61d ago
The Identity Trap in EEG Foundation Models: A Diagnostic Audit
61d ago
Capturing non-Markovian dynamics in non-equilibrium stochastic systems using flow matching
61d ago
Explainable Runtime Dependency Tracking for AI-RAN Conflict Monitoring
61d ago
Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning
61d ago
Spatiotemporal Imputation with Graph-Informed Flow Matching
61d ago
Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers
61d ago
The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search
61d ago
RECAP: Regression Evaluation for Continual Adaptation of Prompts
61d ago
ShallowBench: Benchmarking Generative Drug Design Models on Shallow-Pocket Targets
61d ago
MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detection
61d ago
Early Detection of Alzheimer's Disease Using Explainable Machine Learning on Clinical Biomarkers: A Multi-Class Classification Study Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) Dataset
65d ago
Novel Aspects of IEEE SA P3109 Arithmetic Formats for Machine Learning
65d ago
Position: Deployed Reinforcement Learning should be Continual
65d ago
Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent
65d ago
Do Transformers Need Three Projections? Systematic Study of QKV Variants
65d ago
Inverse Critical Experiment Design via Gradient Optimization and a Multigroup Attention-Based Neural Network Architecture
65d ago
Self-Distilled Policy Gradient
65d ago
Bayes-Sufficient Representations in Supervised Learning
65d ago
Unlocking Feature Learning in Gated Delta Networks at Scale
65d ago
LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection
65d ago
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
65d ago
A Goal-Set Characterization of Task Composition in the Boolean Task Algebra
65d ago
Spectral Scaling Laws of Muon
65d ago
LLM Compression with Jointly Optimizing Architectural and Quantization choices
65d ago
TPA-AD: A Two-Stage Pseudo Anomaly-Guided Method for Bearing Time-Series Anomaly Detection
65d ago
Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting
65d ago
Large Language Models Hack Rewards, and Society
65d ago
Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
65d ago
Building The Ph(ysical)AI Layer Of Machine Intelligence
65d ago
Variance Reduction for Heavy-Tailed Monetization Metrics in Ranking Experiments via Post-Stratification
65d ago
Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning
66d ago
Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent
66d ago
Making Brain-Computer Interfaces More Secure
66d ago
Assessing Region-Level EEG Contributions to Cognitive Workload Prediction
66d ago
Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection
66d ago
Graph Mamba Survival Analysis Based on Topology-Aware ordering
66d ago
Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation
66d ago
Cross-Modal Contrastive Learning of ECG and Angiography Representations for Severe Stenosis Classification
66d ago
ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services
66d ago
Geometry-Aware Tabular Diffusion
66d ago
Pruning Deep Neural Networks via the Marchenko--Pastur Distribution
66d ago
Building Better Activation Oracles
66d ago
Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs
66d ago
Regime-Arrival Uncertainty in Generalization Bounds under Distribution Shift
66d ago
CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning
66d ago
Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning
66d ago
AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret
66d ago
Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate
66d ago
Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis
66d ago
Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals
66d ago
BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
67d ago
DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions
67d ago
Hoeffding Concept Bottleneck Models with Applications to Overhead Images
67d ago
From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
67d ago
A Shared Valence Axis Across Modern LLMs and Human EEG: The Saturation Regularity
67d ago
Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks
67d ago
Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization
67d ago
World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications
67d ago
On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
67d ago
Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey
67d ago
Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
67d ago
Adaptive data selection improves wearable prediction under low baseline performance
67d ago
BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
67d ago
RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting
67d ago
Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
67d ago
ChurnNet: A Optimized Modern AI for Churn Prediction
67d ago
Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection
67d ago
Agentic Transformers Provably Learn to Search via Reinforcement Learning
67d ago
AI-Guided Design and Optimization of Graphite-Based Anodes via Iterative Experimental Feedback
67d ago
Learning to Construct Practical Agentic Systems
67d ago
QASM-Eval: A Dataset to Train and Evaluate LLMs on OpenQASM-3 Beyond Quantum Circuits
68d ago
Gait2Hip-60: A Unified Deep Learning Benchmark for Predicting Hip Muscle Forces and Joint Moments from Multi-Cadence Gait Kinematics
68d ago
Unicorn: Scaling High-Dimensional Time Series Forecasting via Universal Correlation Modeling
68d ago
When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception
68d ago
LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study
68d ago
Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification
68d ago
A Novel Evaluation Metric for Unsupervised Learning in AIS-Based Maritime Anomaly Detection: MADQI
68d ago
NumLeak: Public Numeric Benchmarks as Latent Labels in Foundation Models
68d ago
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis
68d ago
Calibrated Preference Learning: The Case of Label Ranking
68d ago
Bounded Behavioral Indistinguishability for Black-Box LLM Distillation
68d ago
VeriGate: Verifier-Gated Step-Level Supervision for GRPO
68d ago
A Unified Framework for Gradient Aggregation in Multi-Objective Optimization
68d ago
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
68d ago
Scalable Constrained Multi-Agent Reinforcement Learning via State Augmentation and Consensus for Separable Dynamics
68d ago
idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
68d ago
Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
68d ago
Universal Multiclass Transductive Online Learning
68d ago
Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability
68d ago
Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
68d ago
One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them
71d ago
Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents
71d ago
Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
71d ago
Molecular Lead Optimization via Agentic Tool Planning
71d ago
Self-Play Reinforcement Learning under Imperfect Information in Big 2
71d ago
Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
71d ago
Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
71d ago
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
71d ago
TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models
71d ago
Balancing Multimodal Learning through Label Space Reshaping
71d ago
Representation Alignment Rests on Linear Structure
71d ago
Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit
71d ago
Towards Continuous-time Causal Foundation Models
71d ago
Context Distillation as Latent Memory Management
71d ago
Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models
71d ago
Spectral Guidance for Flexible and Efficient Control of Diffusion Models
71d ago
Sequential Physics-Constrained Neural Operator Forward Modeling for the $\textit{Norne}$ Reservoir System
71d ago
Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems
71d ago
When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
71d ago
CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models
71d ago
Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity
72d ago
IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation
72d ago
A Simple State Space Model Excels at Multivariate Time Series Classification
72d ago
$E^3$-Agent: An Executable and Evolving Agent for Resource Management of Edge Generative Inference
72d ago
Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey
72d ago
Metric-Aware PCA as a Linear Instance of Geometric Deep Learning
72d ago
Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility
72d ago
Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift
72d ago
Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection
72d ago
HEAL: Resilient and Self-* Hub-based Learning
72d ago
Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective
72d ago
Resource-Constrained Affect Modelling via Variance Regularisation Pruning
72d ago
Energy-Structured Low-Rank Adaptation for Continual Learning
72d ago
Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation
72d ago
GenSBI: Generative Methods for Simulation-Based Inference in JAX
72d ago
SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training
72d ago
The Fundamental Limits of Fraud Detection in Card Payment Networks
72d ago
Information-theoretic Multimodal Representation Learning for Electrocardiogram Signals
72d ago
Gradient Transformer: Learning to Generate Updates for LLMs
72d ago
The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution
72d ago
GEM: Geometric Entropy Mixing for Optimal LLM Data Curation
73d ago
The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models
73d ago
AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion
73d ago
SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection
73d ago
Neural Bayesian Sequential Routing
73d ago
TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models
73d ago
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
73d ago
Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning
73d ago
When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
73d ago
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
73d ago
InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
73d ago
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
73d ago
Max-Window Scale Estimation for Near-Lossless HiF8 W8A8 Quantization-Aware Training
73d ago
HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals
73d ago
Modeling Dynamic Mixtures of Time-Delay Systems from Streaming Time Series
73d ago
Co-folding model guided by structural proteomics
73d ago
Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
73d ago
On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series
73d ago
From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD
73d ago
Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
73d ago
Algometrics: Forecasting Under Algorithmic Feedback
74d ago
Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection
74d ago
CAFD: Concept-Aware DNN Fault Detection using VLMs
74d ago
Towards Verifiable Transformers: Solver-Checkable Circuit Explanations
74d ago
Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
74d ago
Hidden-State Privacy Has an Empty Middle
74d ago
LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
74d ago
A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?
74d ago
Mixture of Complementary Agents for Robust LLM Ensemble
74d ago
Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing
74d ago
Cascade-KDE: Robust Time-Series Restoration under Out-of-Distribution Impulse Corruptions
74d ago
Feature Lottery? A Bifurcation Theory of Concept Emergence
74d ago
Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning
74d ago
Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers
74d ago
Federated Learning over Human-Body Communication for On-Body Edge Intelligence: A Survey, Taxonomy, and BODYFED-HBC Scheduling Vignette
74d ago
Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion
74d ago
Not All Transitions Matter: Evidence from PPO
74d ago
Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
74d ago
Overcoming "Physics Shock" in Earth Observation A Heteroscedastic Uncertainty Framework for PINN-based Flood Inference
74d ago
Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions
74d ago
Latent Cache Flow: Model-to-Model Communication Without Text
75d ago
Reading Calibrated Uncertainty from Language Model Trajectories
75d ago
FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence
75d ago
FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning
75d ago
The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
75d ago
Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity
75d ago
MedExpMem: Adapting Experience Memory for Differential Diagnosis
75d ago
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
75d ago
WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems
75d ago
Tensor Cache: Eviction-conditioned Associative Memory for Transformers
75d ago
Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems
75d ago
From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data
75d ago
FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
75d ago
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
75d ago
Building a privacy-preserving Federated Recommender system for mobile devices
75d ago
Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning
75d ago
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
75d ago
FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data
75d ago
Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization
75d ago
Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
75d ago
Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding
77d ago
Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation
77d ago
The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity
77d ago
Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
77d ago
Double descent for least-squares interpolation on contaminated data: A simulation study
77d ago
HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine
77d ago
Predicting Performance of Symbolic and Prompt Programs with Examples
77d ago
Harnesses for Inference-Time Alignment over Execution Trajectories
77d ago
A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction
77d ago
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
77d ago
Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series
77d ago
Provable Joint Decontamination for Benchmarking Multiple Large Language Models
77d ago
Tabular foundation models for robust calibration of near-infrared chemical sensing data
77d ago
PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting
77d ago
Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
77d ago
TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems
77d ago
Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising
77d ago
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
77d ago
AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems
77d ago
Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection
77d ago
Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
79d ago
GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation
79d ago
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
79d ago
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
79d ago
MagBridge-Battery: A Synthetic Bridge Dataset for Li-ion Magnetometry and State-of-Health Diagnostics
79d ago
Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
79d ago
LEAP: A closed-loop framework for perovskite precursor additive discovery
79d ago
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
79d ago
CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
79d ago
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
79d ago
Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
79d ago
Physics-informed convolutional neural networks for fluid flow through porous media
79d ago
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
79d ago
FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
79d ago
Instance Discrimination for Link Prediction
79d ago
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
79d ago
Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
79d ago
Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding
79d ago
Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity
79d ago
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
79d ago
Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance
80d ago
Robust Basis Spline Decoupling for the Compression of Transformer Models
80d ago
HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models
80d ago
UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing
80d ago
Simply Stabilizing the Loop via Fully Looped Transformer
80d ago
Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
80d ago
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
80d ago
Theory-optimal Quantization Based on Flatness
80d ago
PROWL: Prioritized Regret-Driven Optimization for World Model Learning
80d ago
Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning
80d ago
Block-Based Double Decoders
80d ago
Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect
80d ago
Metric-Gradient Projection for Stable Multi-Agent Policy Learning
80d ago
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
80d ago
PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines
80d ago
Composition of Memory Experts for Diffusion World Models
80d ago
How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines
80d ago
DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training
80d ago
Symmetry in the Wild: The Role of Equivariance in Neural Fluid Surrogates
80d ago
Multi-Token Residual Prediction
80d ago
Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra
81d ago
Mirror Descent-Type Algorithms for the Variational Inequality Problem with Functional Constraints
81d ago
Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
81d ago
SignMuon: Communication-Efficient Distributed Muon Optimization
81d ago
When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning
81d ago
A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning
81d ago
Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning
81d ago
Forecasting Medium-Horizon Alzheimer's Disease Progression: Residual Gap-Aware Transformers for 24-Month CDR-SB Change from ADNI Clinical and Biomarker Histories
81d ago
AdaGraph: A Graph-Native Clustering Algorithm That Overcomes the Curse of Dimensionality and Enables Scientific Discovery
81d ago
Language Game: Talking to Non-Human Systems
81d ago
Bi-Level Chaotic Fusion Based Graph Convolutional Network for Stock Market Prediction Interval
81d ago
Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
81d ago
Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders
81d ago
Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization
81d ago
DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
81d ago
LoopQ: Quantization for Recursive Transformers
81d ago
Goal-Conditioned Supervised Learning for LLM Fine-Tuning
81d ago
PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
81d ago
HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support
81d ago
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
81d ago
AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices
82d ago
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
82d ago
Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
82d ago
Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation
82d ago
MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion
82d ago
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
82d ago
Logical Grammar Induction via Graph Kolmogorov Complexity: A Neuro-Symbolic Framework for Self-Healing Clinical Data Integrity
82d ago
Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design
82d ago
Privacy Evaluation of Generative Models for Trajectory Generation
82d ago
GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding
82d ago
PDRNN: Modular Data-driven Pedestrian Dead Reckoning on Loosely Coupled Radio- and Inertial-Signalstreams
82d ago
Position: Ideas Should be the Center of Machine Learning Research
82d ago
Curriculum Learning of Physics-Informed Neural Networks based on Spatial Correlation
82d ago
Training on Documents About Monitoring Leads to CoT Obfuscation
82d ago
Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
82d ago
Universal Approximation of Nonlinear Operators and Their Derivatives
82d ago
GQA-{\mu}P: The maximal parameterization update for grouped query attention
82d ago
GESD: Beyond Outcome-Oriented Fairness
82d ago
How Data Augmentation Shapes Neural Representations
82d ago
Time-Varying Deep State Space Models for Sequences with Switching Dynamics
82d ago
Vision-Based Runtime Monitoring under Varying Specifications using Semantic Latent Representations
85d ago
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
85d ago
Rethinking Molecular OOD Generalization via Target-Aware Source Selection
85d ago
Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling
85d ago
Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
85d ago
Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning
85d ago
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
85d ago
EMA: Efficient Model Adaptation for Learning-based Systems
85d ago
A Unified Geometric Framework for Weighted Contrastive Learning
85d ago
Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
85d ago
WarmPrior: Straightening Flow-Matching Policies with Temporal Priors
85d ago
Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines
85d ago
TabPFN-3: Technical Report
85d ago
Neural Fields for NV-Center Inverse Sensing
85d ago
HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts
85d ago
Support Before Frequency in Discrete Diffusion
85d ago
Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signal
85d ago
R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning
85d ago
Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility
85d ago
Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
85d ago
Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance
86d ago
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
86d ago
Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
86d ago
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
86d ago
Learning to Decide with AI Assistance under Human-Alignment
86d ago
Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
86d ago
Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
86d ago
Multi-Rollout On-Policy Distillation via Peer Successes and Failures
86d ago
Plan Before You Trade: Inference-Time Optimization for RL Trading Agents
86d ago
scShapeBench: Discovering geometry from high dimensional scRNAseq data
86d ago
ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization
86d ago
Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction
86d ago
A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions
86d ago
IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback
86d ago
Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification
86d ago
UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning
86d ago
Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
86d ago
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
86d ago
A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data
86d ago
Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations
86d ago
Interpretable EEG Microstate Discovery via Variational Deep Embedding: A Systematic Architecture Search with Multi-Quadrant Evaluation
87d ago
QuIDE: Mastering the Quantized Intelligence Trade-off via Active Optimization
87d ago
Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
87d ago
Rotation-Preserving Supervised Fine-Tuning
87d ago
Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
87d ago
Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
87d ago
LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
87d ago
$\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin
87d ago
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
87d ago
Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioning
87d ago
AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines
87d ago
Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
87d ago
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
87d ago
Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures
87d ago
SkillGen: Verified Inference-Time Agent Skill Synthesis
87d ago
Finite Volume-Informed Neural Network Framework for 2D Shallow Water Equations: Rugged Loss Landscapes and the Importance of Data Guidance
87d ago
DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism
87d ago
RT-Transformer: The Transformer Block as a Spherical State Estimator
87d ago
When and How to Canonize: A Generalization Perspective
87d ago
ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network
87d ago
Reinforcement learning for inverse structural design and rapid laser cutting of kirigami prototypes
88d ago
Path-Based Gradient Boosting for Graph-Level Prediction
88d ago
Distributional Reinforcement Learning via the Cram\'er Distance
88d ago
Geometry-free prediction of inertial lift forces in microfluidic devices using deep learning
88d ago
BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models
88d ago
TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data
88d ago
Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa
88d ago
Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant
88d ago
The Safety-Aware Denoiser for Text Diffusion Models
88d ago
Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking
88d ago
Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge
88d ago
Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models
88d ago
Towards Customized Multimodal Role-Play
88d ago
Additive Atomic Forests for Symbolic Function and Antiderivative Discovery
88d ago
Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization
88d ago
DARE: Diffusion Language Model Activation Reuse for Efficient Inference
88d ago
Dendritic Neural Networks with Equilibrium Propagation
88d ago
Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI
88d ago
DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis
88d ago
Reasoning emerges from constrained inference manifolds in large language models
88d ago
RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory
89d ago
LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction
89d ago
A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence
89d ago
Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding
89d ago
On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching
89d ago
A Hierarchical Ensemble Pipeline for Anomaly Detection in ESA Satellite Telemetry
89d ago
Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models
89d ago
From Canopy to Collision: A Hybrid Predictive Framework for Identifying Risk Factors in Tree-Involved Traffic Crashes
89d ago
Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices
89d ago
Conditional generation of antibody sequences with classifier-guided germline-absorbing discrete diffusion
89d ago
Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning
89d ago
Transformer-Based Wildlife Species Classification from Daily Movement Trajectories
89d ago
Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training
89d ago
The E$\Delta$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality
89d ago
Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics
89d ago
On Training in Imagination
89d ago
Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA
89d ago
Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning
89d ago
STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification
89d ago
Geometric Kolmogorov--Arnold Network (GeoKAN)
89d ago
Are Flat Minima an Illusion?
92d ago
Nationwide EHR-Based Chronic Rhinosinusitis Prediction Using Demographic-Stratified Models
92d ago
SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees
92d ago
Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning
92d ago
Horizon-Constrained Rashomon Sets for Chaotic Forecasting
92d ago
Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
92d ago
MidSteer: Optimal Affine Framework for Steering Generative Models
92d ago
Data-Driven Variational Basis Learning Beyond Neural Networks: A Non-Neural Framework for Adaptive Basis Discovery
92d ago
Adaptive Computation Depth via Learned Token Routing in Transformers
92d ago
Structural Instability of Feature Composition
92d ago
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
92d ago
MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
92d ago
Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning
92d ago
Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
92d ago
Evolutionary fine tuning of quantized convolution-based deep learning models
92d ago
Expert Routing for Communication-Efficient MoE via Finite Expert Banks
92d ago
Forecasting Green Skill Demand in the Automotive Industry: Evidence from Online Job Postings
92d ago
Attribution-Guided Continual Learning for Large Language Models
92d ago
Graph Normalization: Fast Binarizing Dynamics for Differentiable MWIS
92d ago
Feature Starvation as Geometric Instability in Sparse Autoencoders
92d ago
Endogenous Regime Switching Driven by Scalar-Irreducible Learning Dynamics
93d ago
A Self-Attentive Meta-Optimizer with Group-Adaptive Learning Rates and Weight Decay
93d ago
Transformation Categorization Based on Group Decomposition Theory Using Parameter Division
93d ago
Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
93d ago
MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
93d ago
Continual Distillation of Teachers from Different Domains
93d ago
Lookahead Drifting Model
93d ago
Single-Position Intervention Fails: Distributed Output Templates Drive In-Context Learning
93d ago
EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation
93d ago
Investigating Trustworthiness of Nonparametric Deep Survival Models for Alzheimer's Disease Progression Analysis
93d ago
Improving Medical VQA through Trajectory-Aware Process Supervision
93d ago
Designing a double deep reinforcement learning selection tool for resilient demand prediction
93d ago
LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment
93d ago
FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing
93d ago
Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
93d ago
Confronting Label Indeterminacy in Automated Bail Decisions
93d ago
A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers
93d ago
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
93d ago
A Regulatory Governance Framework for AI-Driven Financial Fraud Detection in U.S. Banking: Integrating OCC, SR 11-7, CFPB, and FinCEN Compliance Requirements for Model Development, Validation, and Monitoring Lifecycles
93d ago
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
93d ago
StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing
94d ago
eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization
94d ago
An End-to-End Framework for Building Large Language Models for Software Operations
94d ago
On the Invariants of Softmax Attention
94d ago
Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR
94d ago
Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Models
94d ago
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
94d ago
When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models
94d ago
From Synthesis to Clinical Assistance: A Strategy-Aware Agent Framework for Autism Intervention based on Real Clinical Dataset
94d ago
PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL
94d ago
Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection
94d ago
Heterogeneous Graph Importance Scoring and Clustering with Automated LLM-based Interpretation
94d ago
DeRelayL: Sustainable Decentralized Relay Learning
94d ago
Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
94d ago
PAMNet: Cycle-aware Phase-Amplitude Modulation Network for Multivariate Time Series Forecasting
94d ago
From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework
94d ago
PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework
94d ago
A Framework for Exploring and Disentangling Intersectional Bias: A Case Study in Fetal Ultrasound
94d ago
Healthcare AI GYM for Medical Agents
94d ago
Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation
94d ago
Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling
95d ago
Polynomial-Time Optimal Group Selection via the Double-Commutator Eigenvalue Problem
95d ago
Sparse Regression under Correlation and Weak Signals: A Reproducible Benchmark of Classical and Bayesian Methods
95d ago
From Euler to Dormand-Prince: ODE Solvers for Flow Matching Generative Models
95d ago
Fast Log-Domain Sinkhorn Optimal Transport with Warp-Level GPU Reductions
95d ago
GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI
95d ago
StyleShield: Exposing the Fragility of AIGC Detectors through Continuous Controllable Style Transfer
95d ago
Linking spatial biology and clinical histology via Haiku
95d ago
A Review of the Receiver Operating Characteristic Curve and a Proof About the Area Beneath It
95d ago
PhaseNet++: Phase-Aware Frequency-Domain Anomaly Detection for Industrial Control Systems via Phase Coherence Graphs
95d ago
Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design
95d ago
CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
95d ago
Structured Analytic Coherent Point Drift for Non-Rigid Point Set Registration
95d ago
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
95d ago
EventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems
95d ago
Fusing Urban Structure and Semantics: A Conditional Diffusion Model for Cross-City OD Matrix Generation
95d ago
From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
95d ago
Interpretable experiential learning based on state history and global feedback
95d ago
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
95d ago
Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
95d ago
Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference
96d ago
FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources
96d ago
What Physics do Data-Driven MoCap-to-Radar Models Learn?
96d ago
AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G
96d ago
Learning physically grounded traffic accident reconstruction from public accident reports
96d ago
Smart Ensemble Learning Framework for Predicting Groundwater Heavy Metal Pollution
96d ago
Information-Theoretic Generalization Bounds for Stochastic Gradient Descent with Predictable Virtual Noise
96d ago
Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications
96d ago
Soft-MSM: Differentiable Context-Aware Elastic Alignment for Time Series
96d ago
CRADIPOR: Crash Dispersion Predictor
96d ago
Hyperspherical Forward-Forward with Prototypical Representations
96d ago
Comparative Analysis of Polygon-Based and Global Machine Learning Models for Bus Occupancy Prediction
96d ago
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
96d ago
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
96d ago
Smart Profit-Aware Crop Advisory System: Kisan AI
96d ago
Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization
96d ago
Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback
96d ago
Consistent Diffusion Language Models
96d ago
Towards A Generative Protein Evolution Machine with DPLM-Evo
96d ago
Introducing WARM-VR: Benchmark Dataset for Multimodal Wearable Affect Recognition in Virtual Reality
96d ago
1320 loaded
SM
stat.ML updates on arXiv.org
1d ago · 1351 items
Quality Diversity for Reliable Data Driven Time-Use Optimization
1d ago
Abstract page for arXiv paper 2608.05230: Quality Diversity for Reliable Data Driven Time-Use Optimization
A Unified Causal Inference Framework for the Desirability of Outcome Ranking Paradigm in Benefit-Risk Evaluation
1d ago
Abstract page for arXiv paper 2608.05244: A Unified Causal Inference Framework for the Desirability of Outcome Ranking Paradigm in Benefit-Risk Evaluation
Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data
1d ago
Abstract page for arXiv paper 2608.05930: Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data
Handling Missing Data in Probabilistic Regression Trees
1d ago
Abstract page for arXiv paper 2608.06195: Handling Missing Data in Probabilistic Regression Trees
Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
1d ago
Abstract page for arXiv paper 2608.06206: Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
1d ago
Abstract page for arXiv paper 2608.06250: Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning
1d ago
Abstract page for arXiv paper 2608.06276: Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning
Optimal Rates for Learning with Monotone Adversaries
1d ago
Abstract page for arXiv paper 2608.06337: Optimal Rates for Learning with Monotone Adversaries
Scalable estimation of VARMA models
1d ago
Abstract page for arXiv paper 2608.06340: Scalable estimation of VARMA models
FlowAdam: Implicit Regularization via Geometry-Aware Soft Momentum Injection
1d ago
Abstract page for arXiv paper 2604.06652: FlowAdam: Implicit Regularization via Geometry-Aware Soft Momentum Injection
The Loss Does Not See the Basis, but Adam Does
1d ago
Marginal Matching Does Not License Factorized Sampling: Auditing Conditional Style Leakage in Factorized Generative Models
1d ago
Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes
1d ago
Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty
1d ago
Innovation-Residual Auditing of Autonomous Analysis Agents: Localization, Detection Limits, Error Control, and Identifiability
1d ago
Structured Dimension-Matched Joint Variational Transdimensional Inference
1d ago
Fuzzy network jump models for soft dynamic clustering of graph-structured data
1d ago
Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators
1d ago
The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
1d ago
Surv-IPTB: An Attention-Based Model for Estimating Individual Probability of Treatment Benefit with Survival Data
1d ago
Statistical learning theory and Occam's razor: Regularization
2d ago
Automatic Statistical Test for Rationally Expressible Algorithms by Selective Inference, with Applications to Feature Selection
2d ago
Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds
2d ago
Stable Density Ridges: Consistency and Convergence of Subspace Constrained Mean Shift
2d ago
Informational Frustration in Neural Manifolds: Shannon Bottlenecks and the Limits of Learnability
2d ago
Statistical Mechanics of Learning on Product Wasserstein Manifolds
2d ago
Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport
2d ago
When Is a Conformal Guarantee Fair? Auditing Silent Subgroup Under-Coverage in Alzheimer's Disease Longitudinal Prediction
2d ago
Sample Complexity of Multicalibration for Multilevel Properties
2d ago
ArborEnum: Decision Tree Rashomon Sets over Continuous Features
2d ago
Achieving First-Order Statistical Improvements in Data-Driven Optimization: From No-Free-Lunch to Amplified Decision Perturbation
2d ago
Equitable System-Prompt Selection via Constrained Mixed-Strategy GroupDRO
2d ago
iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data
2d ago
Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics
2d ago
Incremental Aggregation on the Grassmannian for Asynchronous Eigenspace Computation
2d ago
An adaptive split-combine Gaussian mixture filter for nonlinear and multimodal state estimation
2d ago
Discretization and Statistical Consistency of Functional Flow Matching
2d ago
An entropic explanation of insistence on sameness in autism
2d ago
Personalized Federated Sparse Adaptation of Time-Series Foundation Models
2d ago
Nonparametric Goodness-of-fit Testing under Covariate Shift
2d ago
A Hyperfinite Framework for Score-Based Generative Modeling
3d ago
Particle-based Generalised Stochastic Optimisation
3d ago
Causal Inference with Unstructured Outcomes
3d ago
Minimax-Optimal Semiparametric Contextual Dynamic Pricing with Multimodal Revenue
3d ago
Conformal risk control for model-form uncertainty in parametric non-intrusive reduced-order models
3d ago
Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking
3d ago
Divide-and-Conquer: Towards Generalizable Amortized Bayesian Inference for the Drift Diffusion Model
3d ago
Robust Low-Tubal-Rank Tensor Completion under Cross-Concentrated Sampling
3d ago
Information-Geometric Forward Policy Training in GFlowNets
3d ago
Neural network realization of binary refinement iterates via a two-chart atlas selector
3d ago
GeoID-PINN: Identifiability-Aware Regional Epidemic Inference with Geographic Coupling
3d ago
Can Training Logs Make Model Comparisons More Precise?
3d ago
DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing
3d ago
Tight Information Complexity of the Coin Problem in the Broadcast Model
3d ago
Improved Quantum Algorithms for Reinforcement Learning Under a Generative Model
3d ago
When Predictions Become Regressors: A Split-Sample Correction for Biases in Downstream Inference
3d ago
Calibrated Bayesian Inference for Stochastic Intervention Effects
3d ago
Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores
3d ago
Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework
3d ago
A Direct Route to Markov Chain Convergence via Asymptotic Equivalence with the Target
3d ago
A reproducible and extensible framework for benchmarking competing risks survival models
4d ago
Causal Inference with Unstructured Treatments
4d ago
Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors
4d ago
Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP
4d ago
How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule
4d ago
Dominant Arm Identification with Mixing and Recycling Observed Samples
4d ago
Finite-Probe Total-Variation Certificates for Finite-Basis Drifting Models
4d ago
The Label Defines the Timescale: Trait-State Limits of Temporal-Aggregate Learning
4d ago
Detecting Nonproperness of Likelihood Equations
4d ago
Private Generative Bootstrap via Blocking
4d ago
Computational and Statistical Guarantees of the \textit{c}-Rectified flow
4d ago
Interaction Is Not Necessary for Order-Optimal 1-Bit Mean Estimation
4d ago
Fast-Mixing Markov Chains without Gradients
4d ago
Bridging extrinsic and intrinsic variable importance
4d ago
Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
4d ago
Backward Bayesian Outcome Weighted Learning
4d ago
Recursive Gaussian Processes and the Bayesian Brain
4d ago
Learning the Pareto Frontier of Predictive Models under Distribution Shift
4d ago
Evolutionary Curriculum Learning Improves Biological Sequence Modeling
4d ago
Physics-informed neural networks for two-dimensional wall-reactive solute dispersion in canonical shear flows
4d ago
Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs
5d ago
Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression
5d ago
Structured Neural Chaos: An Adaptive Surrogate Modeling Framework for Functional Uncertainty Quantification and Global Sensitivity Analysis
5d ago
Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization
5d ago
Simple-regret rates and minimax optimality of fixed-prior expected improvement in Mat\'ern and squared-exponential RKHSs
5d ago
The Greedy Advantage in Finite-Horizon Bandits
5d ago
Analytical and Bootstrap Confidence Intervals of Double Machine Learning: Simulation studies and an application to rural-urban difference in obesity prevalence
5d ago
WaiT for the Signal: Simple Frequency-Aware Flow-Matching
5d ago
Bayesian Mediation Analysis for Individualized Treatment Rules
5d ago
Seeing the Forest for the Trees: The Gaussian Process Limit of BART
5d ago
The Debiased Score Test: Hunt-and-test for Semiparametric Hypotheses
5d ago
Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design
5d ago
Distance Profile Embedding for Independence and Conditional Independence Testing of Random Objects
5d ago
A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-Making and Evaluation
5d ago
Bayesian fusion forests for heterogeneous treatment effects on survival from randomised and real-world data
5d ago
Longitudinal Adaptive Experimental Design for Learning Multiple Target Estimands with Semiparametric Efficient Inference
5d ago
TerraNova: A Foundation Model for the Anthropocene
5d ago
Exponential Capacity in Multilayer Hetero-Associative Neural Networks
5d ago
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
5d ago
Differentially Private Nonparametric Modal Learning with Applications to Regression and Clustering
5d ago
More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility
8d ago
Expected Survival-Time Bounds for Robust Optimization Over Time under Isotropic Gaussian Dynamics
8d ago
An analysis of binary isotonic regression: degrees of freedom and implications for calibration
8d ago
HOMER: Huber-of-Means for Efficient and Robust Estimation in Hilbert Spaces
8d ago
Robust Wavelength Selection for Partial Least Squares Sugar Content Estimation Using Combinatorial Bayesian Optimization
8d ago
Error Analysis of Neural-Network-Based Engression
8d ago
Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
8d ago
Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators
8d ago
On a joint simultaneous learning of relevant feature subsets and subspaces in regression-like problems
8d ago
Uncertainty quantification for trustworthy deep learning: Methods and measures
8d ago
Doubly Robust Functional Representation Learning for Longitudinal Causal Inference with Irregular Histories
8d ago
Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision
8d ago
THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model
8d ago
Adaptive Nystr\"om for Gaussian Process Regression
8d ago
Entropy-Smooth Convex Optimization Cannot Be Accelerated
8d ago
Strategies for Milestone-driven Start-ups in Multi-activity Settings
8d ago
Scalable Graph Coreset Selection via Greedy Sampling
8d ago
A Mathematical Framework for Topological Causal Data Analysis
8d ago
Non-partitioned e-detectors for nonparametric sequential change detection
8d ago
Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata
8d ago
When Kernel Ridge Regression Meets the H\"older-Zygmund Class: Minimax Optimality and Failure of Properness
9d ago
Origins and mitigation of double descent in reduced order modeling
9d ago
Chaos Is a LADDER: Domain Generalization Beyond Invariance via Reweighting
9d ago
Early Failure Prediction from Near-Anomaly Detection: A Proactive Approach
9d ago
Crossing-Free Probabilistic K-Line Forecasts Without Retraining
9d ago
Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents
9d ago
Conformalized Rate-Adaptive Sensing
9d ago
Breaking the Curse with BAND: Nonparametric Distribution Estimation in High Dimensions
9d ago
Feature Bagging Provides Stability
9d ago
PIKS: Universal Physics-Informed Kernel Methods
9d ago
Randomizing the Number of Centers in k-means++
9d ago
Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection
9d ago
Denoising growth complexity: Data geometry and certified schedules for diffusion sampling
9d ago
The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text
9d ago
Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning
9d ago
High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumption
9d ago
Existence-Field Diffusion Model for Spatial Point Processes with Variable Cardinality
9d ago
Universality and Approximation Rates of Graph Neural Networks with Random Features
9d ago
Compactly supported radial basis functions as probability density functions
9d ago
BayesAME: Bayesian Active Model Evaluation
9d ago
Lloyd's $K$-Means Clustering Algorithm Is Frank-Wolfe in Disguise
10d ago
Learning from the Unseen: Offline Reinforcement Learning with Hidden Actions
10d ago
Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields?
10d ago
A Generalized Tangent Approximation based Variational Inference Framework for Strongly Super-Gaussian Likelihoods
10d ago
Multiclass Classification without Labels via Posterior Simplex Geometry
10d ago
Generative Distributionally Robust Optimization
10d ago
Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation
10d ago
Transfer Learning in High-Dimensional Clustering: Minimax Thresholds and Applications in Single-Cell Data
10d ago
Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method
10d ago
Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks
10d ago
Sequential Preconditioned Conjugate Gradient Method for Linear Statistical Models
10d ago
Contextual Deconvolution for Variance-Stable Demand Sensing: Kernel-Modulated Operators in Promotional Retail
10d ago
Generalised Robust Bayes for Joint Inference of Model and Contamination
10d ago
Bias-corrected Cox regression with AI-extracted covariates via calibration summary statistics
10d ago
The Barron-Lipschitz Energy Gap and Depth Separation Phenomena in Scientific Machine Learning
10d ago
Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm
10d ago
Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance
10d ago
On the Convergence Analysis of Muon
10d ago
TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models
10d ago
Extreme Event Aware ($\eta$-) Learning
10d ago
TLRNet: Estimating Individual Treatment Effect based on Local Information and Single Learner Structure
11d ago
Amortized Bayesian Causal Discovery of Extended Factor Graphs
11d ago
Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model
11d ago
Variable Importance Identification Through Lazy Training for Binary Classification
11d ago
Robust Conformalized Selection with Noisy Responses
11d ago
Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities
11d ago
Operator Neural Jump ODEs: $L^2$-optimal prediction in function spaces
11d ago
Adaptive Multi-Scale Forecasting and Gate-Localized Conformal Prediction for Multivariate Nonstationary Time Series
11d ago
Beyond ICA: Identifiability by Symmetry Breaking
11d ago
FedSLIM: Privacy-Preserving Federated MDL-Based Descriptive Pattern Mining Across Data Silos
11d ago
Learning Asymptotics with Convergence-Rate Guarantees using Linear Least Squares
11d ago
Context-Adaptive Inference: A Unified Statistical and Foundation-Model View
11d ago
Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data
11d ago
Two-Timescale Hierarchical Reinforcement Learning for Resilient Operations
11d ago
Learning switched non-linear dynamical systems from a single trajectory
11d ago
Distributional Split Criteria for Random Forests: Extensions, Shrinkage, and the Robustness of Mean Splitting
11d ago
On Non-Stationary Dynamic Pricing: Adaptivity and Optimality
11d ago
Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD
11d ago
proxymate: Diagnosis and Adjustment of Proxy Estimates for Reliable Inference
11d ago
Frequency-Based Reservoir computing
11d ago
Prior laundering: learned priors with inherited, undetectable overconfidence
12d ago
Simulation-Based Empirical Bayes
12d ago
Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes
12d ago
Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model
12d ago
Variational Low-rank Tensor Decomposition for Multisubject Spatiotemporal Data Analysis
12d ago
General Value Functions for Remaining Useful Life and Failure-Mode Prediction
12d ago
Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting
12d ago
Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks
12d ago
Learning Ergodic Dynamical Systems from a Finite Trajectory
12d ago
Graph-Based Correlation Matrix Generation: A Convex Optimization Approach
12d ago
CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference
12d ago
Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration
12d ago
An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning
12d ago
A Defense of the Quadratic Model
12d ago
Longitudinal Random Forests for Sparse and Irregular Response Trajectories
12d ago
Reconstruction of Enhanced Causal Omnidirectional Network (RECON)
12d ago
Toward High-Fidelity 3D Point-Cloud Learning for Brain Folding Morphology Prediction Using Trans-Unet
12d ago
Distributional Determinantal Point Process for Repulsive Clustering of Distributions
12d ago
Scaling Laws for Classical Machine Learning on Tabular Data: A Benchmark Study
12d ago
From Score Approximation to Distribution Approximation in Score-Based Diffusion Models
12d ago
SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting
15d ago
Automatic knot selection in smooth additive models
15d ago
Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting
15d ago
Generative Bayesian Filtering for State Estimation
15d ago
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
15d ago
CLOE: Christoffel Loss Autoencoder for Anomaly Detection
15d ago
Fisher Widths: Local Learning Geometry and Anisotropic Recovery
15d ago
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers
15d ago
High Minima of Gaussian Processes: Overshoots and Minimizer Locations
15d ago
Twoblock clustering trees with coskewness-based dimension reduction: recovering piecewise multivariate linear regimes
15d ago
Self-Balancing Sequential Sampling: Fast Convergence with Controlled Predictability
15d ago
Smooth Neural Point Processes via B-Splines
15d ago
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
15d ago
Cautious optimism for deep parameterized quantum circuits
15d ago
Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
15d ago
Finite-Sample Coverage Audits for High-Recall Candidate Generation: Certification and Learning-Theoretic Design
15d ago
Optimal use of a black-box learner in semiparametric estimation
15d ago
Zero-Flow Two-Sample Tests
15d ago
Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Ghana
15d ago
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
15d ago
A Bayesian Framework for Built-in Input Dimension Reduction for Gaussian Process Modeling
16d ago
Boltzmann-Expected Molecular Design with Decoupled Annealing Flows
16d ago
RELTA-SGLD: Relative-Growth Localized Taming for Nonconvex Stochastic-Gradient Langevin Learning
16d ago
Optimal Recalibration of an Online Predictor
16d ago
Data-Poisoning Audits for Causal Effect Estimation
16d ago
Non--negative matrix factorization using the \textit{R} package \textsf{nnmf}
16d ago
Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparison
16d ago
Statistical Inference for Rank Allocation in Low-Rank Adaptation
16d ago
Adaptive Bayesian Online Learning via Expert Aggregation
16d ago
Adaptive deep nonparametric regression from dependent data under covariate shift
16d ago
Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions
16d ago
Bayesian Wind Tunnels for Model Selection
16d ago
Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics
16d ago
Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
16d ago
Total Variation Distance Estimation in Autoregressive Models
16d ago
Deep Shape Regression for Planar Curves with Multimodal Covariates
16d ago
Efficient Clustering with Provable Guardrails for LLM Inference at Scale
16d ago
Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence
16d ago
Active Inference as a Convex Markov Decision Process
16d ago
Quantum Kernels and the Cross-Section of Stock Returns: Anatomy of a Vanishing Advantage
16d ago
Disentangling Forced and Internal Climate Variability in Single Realizations using Dynamic Mode Decomposition with Control
17d ago
Mixing-Free and Signal-Optimal Learning of Gaussian Graphical Models from Glauber Dynamics
17d ago
The Price of Hidden Curvature: An $\widetilde{\Omega} (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization
17d ago
Algebraic Signatures for Structural Learning in Probability Tensors
17d ago
The Tractability Landscape of Sampling with Inexact Scores
17d ago
Fundamental limits of distributed multiclass classification from simple binary decisions
17d ago
PAC--Bayes Bounds on Quotient Parameter Spaces: Geometry-induced Implicit-Bias Priors
17d ago
Using binary silver labels in electronic health records-based computable phenotyping algorithms
17d ago
Uncertainty quantification in mechanics: A unified Bayesian perspective
17d ago
Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posterior
17d ago
Optimizing Regret
17d ago
Deep learning-based prediction of time-resolved adhesive forces in viscoelastic Hertzian contacts
17d ago
On the sensitivity of machine-learned probabilistic weather forecast models to scale-aware scoring rules
17d ago
Boundary-Adapted PINNs for Elliptic Dirichlet Problems: $H^2(\Omega)$ A Priori Error Bounds with Application to Mean Escape Time Computation
17d ago
Some cautionary tales about Bayesian predictive inference
17d ago
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
17d ago
Generalized Least Squares Kernelized Tensor Factorization
17d ago
Low-Rank Evolutionary Deep Neural Networks via Adaptive Tangent-Space Reduction
17d ago
Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness
18d ago
MTSSL: Meta-Thresholding Semi-Supervised Learning
18d ago
Backpropagation-Free Trunk Training via the Split Forward Gradients
18d ago
Isotonic Conformal Prediction
18d ago
Semi-Supervised Conditional Diffusion via Label Augmentation
18d ago
A Causal Markov Condition for Value
18d ago
Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations
18d ago
Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets
18d ago
Deep Adaptive Bayesian Screening
18d ago
Twisted Schr\"odinger Bridge Matching
18d ago
Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning
18d ago
Kernel Regression with Tensor Trains and Hadamard Overparameterization
18d ago
Efficient Sequential Evaluation of Large Language Models
18d ago
An efficient adaptive dimension selection algorithm for multidimensional probit graded response models
18d ago
An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers
18d ago
COVAriance-Induced Fairness Gap Penalty for Subgroup-Fair Clustering
18d ago
Classification Trees with Valid Inference via the Exponential Mechanism
18d ago
Quantifying Ranking Uncertainty in LLM Benchmarks
18d ago
Reducing Per-Sample Harm in Stochastic Optimization
18d ago
Scaling Limits of Constant-Stepsize SGD at Flat Minima
18d ago
Design-Based Supervised Learning with Noisy Human Labels
19d ago
Retraining Seeks Stable Signals
19d ago
Which Hyperparameters Matter? A Game-Theoretic Framework for Interpretable Hyperparameter Sensitivity Analysis
19d ago
Deep and Probabilistic Models for Gene Regulatory Network Inference
19d ago
Cluster-Aware Matching via Laplacian Optimal Transport
19d ago
Proactive Inpatient Bed Requests for Emergency Department Admissions
19d ago
Prediction-Only Distillation in Linear and Logistic Regression
19d ago
Diffusion models recover accurate mixture weights despite score function insensitivity
19d ago
On the Role of Normalization in Binary Iterative Hard Thresholding for 1-bit Compressed Sensing
19d ago
Do Generative Models Keep Time? A Time-Aware Evaluation of Synthetic Sequential Tabular Data
19d ago
ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Language
19d ago
Aggregation of Statistical Evidence under Exchangeability
19d ago
Dimension-invariant uniform consistency of the empirical spatial distribution function and its associated spatial depth estimator
19d ago
An Efficient Likelihood Ratio Test for Online Changepoint Detection in the Presence of Autocorrelation
19d ago
Manifold Dimension Estimation via Local Graph Structure
19d ago
Improving Backward Conformal Prediction via Non-Conformity Score Transformation
19d ago
Conformal Graph Prediction with Z-Gromov-Wasserstein Distances
19d ago
Generalized Neural Distributional Regression
22d ago
Operator-Informed Gaussian Processes for Complex Helmholtz Wavefields: From Synthetic Benchmarks to In Vivo Brain Elastography
22d ago
Spectral Concentration and Recovery in Sparse High-Dimensional Random Geometric Graphs
22d ago
Optimal Self-Distillation for Rectified Flow via Linear Probing
22d ago
cGAP: Generalized Association Plots with HOMALS-Guided Heatmaps for Visualization of High-Dimensional Categorical Data
22d ago
Subjective Risk Decomposition: A New View for Uncertainty Quantification
22d ago
PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
22d ago
A Temporal Machine Learning-Based Time-to-Event Model for Predicting ALS Progression and Healthcare Utilization
22d ago
Parsimonious Mixtures of Skewed Bilinear Factor Analyzers
22d ago
NeuralChaos: Optimal Adapted Approximation of Square Integrable Predictable Processes
22d ago
Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion
22d ago
Precise sample covariance spectral norm error -- an RDT view
22d ago
Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers
22d ago
Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data
22d ago
Sharp Stability Threshold and Certification for Designing Stable Residual Architectures
22d ago
What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity
22d ago
GAttNHP: Group Attention Neural Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs
22d ago
Post Hoc Inference for Component Attribution in Multivariate Change-Point Detection
22d ago
Tamed Stochastic Gradient Hamiltonian Monte Carlo
22d ago
Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin
22d ago
Price of Fairness in Bandits: A Tight Minimax Characterization
23d ago
Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration
23d ago
Parallel gradient boosting for flexible estimation of conditional distributions
23d ago
Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
23d ago
Wasserstein gradient flows for Coulomb discrepancies
23d ago
What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry
23d ago
Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
23d ago
Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis
23d ago
Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs
23d ago
Cluster with Auctions for Vector Search
23d ago
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
23d ago
Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations
23d ago
Heavy-Tailed Flow Matching via Random Clocks
23d ago
Verifying formulas for interventional distributions
23d ago
Plausible Deniability Guarantees for Whistleblowers
23d ago
Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression
23d ago
Linear Independent Component Analysis via Optimal Transport
23d ago
Adaptive Conformal Inference through the Lens of Blackwell Approachability
23d ago
Leveraging Differentiable PDE Solvers for Semi-Neural Spatial Reconstruction From Sparse Measurements
23d ago
Convergence Rates for Distribution Matching with Sliced Optimal Transport
23d ago
Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection
24d ago
Learning the Graphical Nature of Symmetries
24d ago
Dynamic Online Processor-Native Inference for State Estimation
24d ago
Falsifying Causal Graphs With Outlier Events
24d ago
Thompson Sampling Is 2-Competitive for Mistakes
24d ago
Contrast-Free ICA and Causal Inference via Wasserstein Distances to the Gaussian
24d ago
ANGLE: Angular Neural Generative Learning via Engression
24d ago
Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo
24d ago
LatentFlow: A General Framework for Conditioning Stochastic Processes
24d ago
Ensemble Controlled-Flow Filtering for Implicit Data Assimilation
24d ago
Removable Defects: The Economics and Limits of Deliberate Deficiency
24d ago
Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs
24d ago
Causal Graphs, Markov Properties and Do-calculus for Stochastic Differential Equations
24d ago
Cluster-Weighted EDMD
24d ago
Forecasting Inflation with Microdata: An Adaptive Machine Learning Approach
24d ago
Statistical Properties and Power Analysis of Divergence Measures for Credit Risk Model Monitoring
24d ago
PolarBM: Complex-valued Boltzmann Machine for Modeling Audio Signals in Polar and Log-polar Coordinates
24d ago
Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise
24d ago
What Does Goodness Measure? A Likelihood-Ratio Account of Forward-Forward Learning
24d ago
MixCIT: A Kernel Based Local-Polynomial Debiased Test for Conditional Independence on Mixed-Type Data
24d ago
Manifold Constrained Conformal Prediction for Spatial Events
25d ago
TSCoNet: A Two-Stage Copula CNN-LSTM for Uncertainty-Aware Spatio-Temporal Forecasting
25d ago
Integrating Background Knowledge for Scalable Causal Discovery
25d ago
Representation Learning for Semiparametric Causal Mediation Analysis under No Essential Heterogeneity
25d ago
Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering
25d ago
Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width
25d ago
Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization
25d ago
Edge Cluster Expansion with Radial Rotary Attention for Interatomic Potentials
25d ago
Long-Memory Reservoir Computing for Data-Scarce Dengue Forecasting
25d ago
Diversified Multinomial Logit Contextual Bandits
25d ago
Manifold Constrained Tabular Deep Neural Networks
25d ago
Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data
25d ago
Conservation Laws for Diffusion Models
25d ago
Energy-guided Recursive Model
25d ago
The Differential Neural Tangent Kernel and Its Positivity
25d ago
Learning from Local Walks on Dynamic Graphs with Bandit Feedback
25d ago
An Extreme Value Perspective on Learning Stress Laws
25d ago
GNet: A scalable and flexible Gaussian process network with nonparametric neurons
25d ago
Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures
25d ago
The Spectral Structure of Latent Treatment Effects
25d ago
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
26d ago
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
26d ago
Spectrally Deconfounded Gradient Boosting
26d ago
Characterization of the basin of convexity for multi-snapshot spike deconvolution via variable projection
26d ago
Deep Gaussian Processes on Directed Acyclic Graphs
26d ago
Adaptive Bayes exactly tracks information over intrinsic time
26d ago
A Statistical Test for the Benefits of Personalizing Interventions
26d ago
Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity
26d ago
Stochastic Linear Bandits with Partially Observed Actions
26d ago
Optimal Top-$k$ Identification from Pairwise Comparisons
26d ago
Achieving Almost Exact Recovery in Almost Quadratic Time: Rank-Based Graph Matching via Local Tree Correlation Tests
26d ago
Solving Stochastic Fixed-Point Equations with High Probability
26d ago
Similarity search generalisation in contrastive learning with InfoNCE loss
26d ago
comprisk: A scikit-learn-compatible Python toolkit for competing-risks survival analysis
26d ago
Near-optimal node-private community estimation in polynomial-time
26d ago
Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions
26d ago
Neural Collapse Is Forbidden: Information Floors in Language Models
26d ago
Terminal Dimension Reduction for Time Series with Applications
26d ago
Statistically Undetectable Backdoors in Deep Neural Networks
26d ago
High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations
26d ago
The Regularization Parameter: Sparse Precision Matrix Estimation
29d ago
Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation
29d ago
Expressivity and Statistical Trade-offs in Diffusion Policy Learning
29d ago
Bayesian Experimental Design via Score Matching
29d ago
Prediction-Powered Active Testing
29d ago
Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning
29d ago
High-Dimensional Procrustes Matching via Tree Counts
29d ago
Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling
29d ago
Mathematical methods of reinforcement learning
29d ago
LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks
29d ago
A law of robustness for two-layer neural networks with arbitrary weights
29d ago
Mixtures of spatial factor analyzers for tensor-variate data
29d ago
Reinforcing the Generation Order of Multimodal Masked Diffusion Models
29d ago
Joint estimation of high-dimensional spiked covariance matrices via a partially shared subspace
29d ago
Selecting Interpretable Circular Coordinates from Data
29d ago
Structure Learning on Clustered Data
29d ago
An interpretable Good--Turing restart criterion for k-means++
29d ago
A scalable version of MADD for big-data classification
29d ago
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
29d ago
Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks
29d ago
Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set
30d ago
Fast determinantal sampling on general spaces and diffusion geometry
30d ago
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
30d ago
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
30d ago
Finding a stationary point of a stochastic convex problem
30d ago
Tensorized algorithms and scalable filtering methods for hidden Markov and factorial hidden Markov models
30d ago
DiPhon: Diffusion on Graphons for Scalable Graph Generation
30d ago
Statistical inverse learning and $\ell^1$-regularization
30d ago
A Unified Detection Framework for AI-Related Content and Artifacts
30d ago
A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It
30d ago
From Jumps to Signatures: a Generative Method for Temporal Point Processes
30d ago
Best-Arm Identification with Generative Proxy
30d ago
Transfer Learning for Linear Discriminant Analysis with a Shared Classification Signal
30d ago
Local large deviations for linear-region growth in random piecewise-linear networks
30d ago
Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
30d ago
The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought
30d ago
Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization
30d ago
Avoiding unsafe sets when training with Langevin Dynamics
30d ago
Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer
30d ago
Optimal Conformal Prediction under Epistemic Uncertainty
30d ago
Higher-Order Certified Robustness for Regression
31d ago
Deep Neural Variation Spaces: A Unifying Perspective on Depth and Complexity
31d ago
To Retain or to Adapt? Generalizing Continual Learning
31d ago
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
31d ago
Width-Robust Learnability in Mean-Field Bayesian Neural Networks
31d ago
Boosting with List-Decodable Codes
31d ago
On the convergence of graph Laplacians with a symmetric divergence
31d ago
Separation Capacity of Scattering Networks on Low-Dimensional Datasets
31d ago
A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems
31d ago
A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel
31d ago
Exact computation of posterior distribution of mixture weights in hierarchical Bayesian models
31d ago
No Subspace to Track: Non-Identifiability and Optimizer State in Low-Rank Training
31d ago
Stochastic generator of trajectories from record data: application to the fluctuations of a glacier's frontal position from a sample of moraines
31d ago
Closed-form fractional radial links for elliptical Mahalanobis discriminant analysis
31d ago
Quantitative Gaussian-Process limits of Tensor Programs
31d ago
A unified perspective of Gaussian process approximation for differential equations
31d ago
Approximate Risk Minimization Over Shrinking-Thresholding Rules in Normal Mean Estimation
31d ago
Factor-Augmented Machine Learning Panel Regressions
31d ago
Feature Learning for the High Dimensional Stationary Sch\"odinger Equation with Deep Ritz Method
31d ago
EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning
31d ago
CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
32d ago
Benign Overfitting Does Not Occur in Diffusion Models
32d ago
Contaminated Multi-task Learning with Heterogeneity: Fundamental Limits and Optimal Algorithms
32d ago
Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions
32d ago
A Hierarchy of Policy Learning Problems
32d ago
Missing Data Imputation under Manifold Hypothesis
32d ago
Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch
32d ago
Robust Bayes-Assisted Conformal Prediction
32d ago
Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis
32d ago
Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models
32d ago
On Pairwise Quantile Regression -- Statistical Guarantees and Applications
32d ago
Tightening the Score Matching Gap for Diffusion Models
32d ago
Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data
32d ago
Integrating Neural Encoders in Bayesian Generalized Linear Mixed Models for Multimodal Data
32d ago
Decomposition for Bayesian Networks: Local and Parallel Inference
32d ago
Wasserstein Residuals: Learning Gradient Flows from Population Dynamics
32d ago
Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
32d ago
Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling
32d ago
Context-Constrained Transfer Learning for Tabular Foundation Models via Data Distillation
32d ago
Geometric Causal Models
32d ago
eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions
36d ago
Full Bayesian Reinforcement Learning via LF-IBIS
36d ago
Statistical Properties of $k$-means Clustering for Data Missing Completely at Random
36d ago
Autorelevance function and other feature relevance measures for univariate time series
36d ago
Born Discrete, Made Smooth: Variational Formulation of Shallow Neural Networks
36d ago
Prediction Sets for Counterfactual Decisions: Coverage, Optimality, and Conformal Prediction
36d ago
An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility
36d ago
The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry
36d ago
From Approximation to Emergence: A Theory of Deep Learning
36d ago
Conditional Inference Trees and Forests for Feature Selection
36d ago
How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size
36d ago
Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness
36d ago
Learning Effective Soliton Dynamics from Scattering Data
36d ago
Identifiability Limits of Physics-Informed Inference for Spatial Stochastic Dynamics from Static Snapshots
36d ago
Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning
36d ago
Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Model
36d ago
Moment-Based Selection of Multiresponse Linear Mixed-Effects Models
36d ago
Sequential Structure-Sensitive Residual Diagnostics for PDE Inverse Problems
36d ago
Conformal Bayes for Two-Sided Censored Gaussian Regression under Label Shift
36d ago
Aggregation with Exponential Weights is Optimal in Expectation
36d ago
From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
37d ago
Neural Network-Based Estimation of Time-Dependent Parameters in AR(p) Processes
37d ago
Hierarchical Variational Kalman Filtering
37d ago
Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
37d ago
Function-Counting Theory for Low-Dimensional Data Structures
37d ago
Characterizing and Identifying Separable Graphical Models
37d ago
Measuring Racial Disparities in Rent Growth Under Algorithmic Landlord Concentration in U.S. Metros
37d ago
Uniform-in-time Propagation-of-Chaos for Stein Variational Gradient Descent
37d ago
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
37d ago
Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent
37d ago
Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics
37d ago
Distributionally Robust Linear Regression With Block Lewis Weights
37d ago
Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning
37d ago
Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization
37d ago
Prototype Language Models
37d ago
From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research
37d ago
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
37d ago
Approximate full-conformal multi-task regression with reproducing kernels
37d ago
Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry
37d ago
Decision-Aware Training for Sample-Based Generative Models
37d ago
Separation Capacity of Scattering Networks
38d ago
Dynamic Prediction of Alternating Recurrent Events via Neural Network
38d ago
SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates
38d ago
Dynamic Gaussian Processes and the Vanilla-SPDE Exchange
38d ago
MNAR-$k$-means: A $k$-means Clustering for Data Missing Not at Random with Magnitude-Decaying Probability
38d ago
Accelerating Conformal Prediction via Approximate Leave-One-Out
38d ago
MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis
38d ago
Horseshoe Priors for Spatial Small Area Estimation: Regular Variation, Tail Robustness, and Deep Learning
38d ago
Accelerometry-Derived Digital Biomarkers for Cardiometabolic Risk: A Population-Representative Tabular Benchmark with Uncertainty Quantification
38d ago
Predictable GRPO: A Closed-Form Model of Training Dynamics
38d ago
Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Product of Random Matrices
38d ago
A Stationary-Distribution Theory for Triplet-Based Plateau Search in Random Forest Ensemble-Size Selection
38d ago
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
38d ago
Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization
38d ago
Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
38d ago
Can Tabular In-Context Learners Generalize to Biomolecular Property Prediction?
38d ago
Learning Gaussian Graphical Models from a Glauber Trajectory Without Mixing
38d ago
Sequential sparse Gaussian process quantile regression
38d ago
Contextual Slate GLM Bandits with Limited Adaptivity
38d ago
On the Convergence of Self-Improving Online LLM Alignment
38d ago
Spectral Perturbation of the Empirical Fisher Information Matrix under Weight Quantization
39d ago
Adaptive Iterative Hard Thresholding for Online High-dimensional Quantile Regression
39d ago
Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms
39d ago
Perspectives on Latent Factor Indeterminacy and its Implications for Data Representation
39d ago
A Bayesian latent Gaussian process framework for aerodynamic uncertainty quantification
39d ago
Connectivity Estimation using Stochastic Graph Heat Modelling
39d ago
Generalization Analysis of Transformers in Distribution Regression
39d ago
Gradient boosting with vector-valued leafs
39d ago
Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery
39d ago
Bidirectional Autoregressive Latent Diffusion for Forward and Inverse Magnetohydrodynamics
39d ago
Adjusted Wasserstein distances for bridging empirical and true distributions with applications to MDS
39d ago
Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{\"o}dinger bridge
39d ago
Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions
39d ago
Extrapolating from Regularised Solutions for Solving Ill-Conditioned Linear Systems in Machine Learning
39d ago
A Stochastic--Geometric Theory of Scaling Laws in Grokking
39d ago
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
39d ago
Non-parametric recovery of causal diffusion mechanisms from steady-state observations
39d ago
Factorizable Normalizing Flows for parameter-dependent density morphing
39d ago
Doubly Robust Adaptive Conformal Inference for Causal Effects Under Temporal Dependence
39d ago
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
39d ago
Directed Graph Topology Inference via Graph Filter Identification
40d ago
The Decision Geometry of Covariance Estimation for the Global Minimum-Variance Portfolio under Heavy Tails
40d ago
Adversarial Contamination Meets Hard Thresholding: An Iterative Algorithm with Signal Adaptivity and Minimax Optimality
40d ago
Local Fokker--Planck Geometry for Score Estimation: Heat-Ball Mean-Value Representations and Exact High-Dimensional Sampling
40d ago
Surprises in Proper Positive-Only Learning
40d ago
Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings
40d ago
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
40d ago
Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
40d ago
How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks
40d ago
VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing
40d ago
Towards Reliable Recommender Systems for Rating Data
40d ago
Supervised Quadratic Feature Analysis: Information Geometry Approach for Dimensionality Reduction
40d ago
Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models
40d ago
Non-Linear Model-Based Sequential Decision-Making in Agriculture
40d ago
Self-Concordant Perturbations for Linear Bandits
40d ago
Trustworthy Predictive Distributions for Tail Events with Semiparametric Diagnostic Transport Maps
40d ago
Deep Residual Networks Learn the Geodesic Curve in the Wasserstein Space
40d ago
Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding
40d ago
The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples
43d ago
A probabilistic framework for online test-time adaptation
43d ago
XMSE-Aware Adaptive Empirical Bayes Estimation
43d ago
Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference
43d ago
Ribbon: Scalable Approximation and Robust Uncertainty Quantification
43d ago
When are likely answers right? On Sequence Probability and Correctness in LLMs
43d ago
Statistical and Structural Approaches to Algorithmic Fairness
43d ago
Explainable Outlier Detection for Interval-valued Data
43d ago
Learning Probabilistic Filters with Strictly Proper Scoring Rules
43d ago
$\lambda$-PSD: Scalable Approximate SNR-Optimised Polynomial Stein Discrepancies
43d ago
Scalable Operator Learning via Nystr\"om Approximation With Denoising Applications
43d ago
Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork
43d ago
Data-Driven Duration Management -- Term Structure Forecasting Using Machine Learning
43d ago
Asymptotically Optimal Learning for Parametric Prophet Inequalities
43d ago
Decision-Aligned Evaluation of Uncertainty Quantification
43d ago
The Geometry of Updates: Fisher Alignment at Vocabulary Scale
43d ago
Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity
43d ago
All you need is log
43d ago
No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference
43d ago
Theory of the Frequency Principle for General Deep Neural Networks
43d ago
Minimax PAC Bounds for Learning in Exogenous Contextual MDPs
44d ago
Stabilizing black-box algorithms through task-oriented randomization
44d ago
Statistically Valid Hyperparameter Selection: From Tuning to Guarantees
44d ago
Gaussian Mean Field Variational Inference can Overestimate Predictive Variance
44d ago
FedReLa: Imbalanced Federated Learning via Re-Labeling
44d ago
When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?
44d ago
A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging
44d ago
Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation
44d ago
Information from coincidences
44d ago
Hierarchical Partial-Order Models for Ranking
44d ago
Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models
44d ago
Efficient Adaptive Data Acquisition via Pretrained Belief Representations
44d ago
Learning Interpretable Text Signals for Structured Responses
44d ago
A functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting
44d ago
Deviance-style normalization for jointly overdispersed counts
44d ago
Robust Linear Predictions: Analyses of Uniform Concentration, Fast Rates and Model Misspecification
44d ago
Structured Approximations of Measures
44d ago
Adaptive Cumulative Mass Calibration with Conformal Prediction
44d ago
Symmetric Linear Dynamical Systems are Learnable from Few Observations
44d ago
Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data
44d ago
Automated Residual Plot Assessment With the R Package autovi and the Shiny Application autovi.web
45d ago
Model selection with proper scoring rules on data sets of time series
45d ago
The Degeneracy Distillery
45d ago
Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data
45d ago
Stochastic Expectation Maximization for Robust State-Space Radio Interferometric Imaging
45d ago
A Dual Edge Spatial Jacobian Image Graph for Interpretable Diabetic Retinopathy Grading
45d ago
When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews
45d ago
A Step Towards Inherently Interpretable Causal Machine Learning Models For Decision Support
45d ago
Data Augmentation: A Fourier Analysis Perspective
45d ago
NoLimits.jl: Flexible and Composable Nonlinear Mixed-Effects Modeling in Julia
45d ago
History estimation in random recursive trees: Pointwise approach via iterated Jordan centralities
45d ago
A Differentially Private Weighted Empirical Risk Minimization Procedure and its Application to Outcome Weighted Learning
45d ago
Predictive variational inference: Learn the predictively optimal posterior distribution
45d ago
LLMs are Bayesian, In Expectation, Not in Realization
45d ago
An adaptive subsampling method for large-sample feature screening
45d ago
Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning
45d ago
Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces
45d ago
Evaluation Metrics as Averaged Outcomes of Fair Gambles
45d ago
Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components
46d ago
Betting on Moments: Legendre Jumper Martingales for Online Exchangeability Testing
46d ago
Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning
46d ago
Diffusion-Driven State Space Models
46d ago
Bayesian Model Averaging under Predictor Redundancy via Density-Ratio Posterior Compression
46d ago
Two Layers of Instability in Causal Estimation
46d ago
Orthogonal Discrepancy Kernels for Learning with Partial Physics
46d ago
Subsampling for supervised learning in reproducing kernel Hilbert spaces
46d ago
Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design
46d ago
Signed Evidence Flow: Conflict-Aware and Stability-Calibrated Data Analysis
46d ago
Variance-Tilted Diffusion Models for Diverse Sampling
46d ago
Convergence Analysis of Nystr\"om Subsampling in Covariate Shift Adaptation for Misspecified case
46d ago
Null-Calibrated Conformal Selection via Target-Membership Scores
46d ago
Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
46d ago
Robust Diffusion Models via Divergence-Induced Weighted Denoising
46d ago
Scalable Bayesian Additive Models for Stellar Flare Detection via Amortized Gaussian Process Inference and Hidden Markov Models
46d ago
Statistical Inference for Misspecified Contextual Bandits
46d ago
Data Evolution by Wittgenstein's Rule Following
46d ago
Domain Adaptation Under Wireless Network Constraints: When Does It Become Green?
46d ago
Time Series Classification through Diffeomorphic Time Warping (DiffTW)
46d ago
The Representational Limit of Scalar Interactions: An Interventional Decomposition
50d ago
A Solver-Free Training Method for Predict-then-Optimize
50d ago
Variational Consensus Monte Carlo for Bayesian Mixture
50d ago
AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing
50d ago
Stochastic Linear Contextual Bandits with Bounded Noise: A Set-Membership Approach
50d ago
AK-MCS-C2 : Active Kriging Monte Carlo Simulation method with conformal certification for failure probability estimation
50d ago
Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random
50d ago
Statistical Properties of Training & Generalization
50d ago
SSH-Net: A Deep Neural Network for Predicting Failure Time Distribution Functions under Competing Risks with Application to GPU Data
50d ago
Computational Identifiability
50d ago
Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale
50d ago
Overfitted high-dimensional matrix factorizations via adaptive spectral shrinkage
50d ago
Machine Learning Integrated in Wavelet Shrinkage (MLShrink)
50d ago
Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction
50d ago
Calibration without labels in multiple testing
50d ago
On the Oracle Complexity of Interpolation-Based Gradient Descent
50d ago
Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning
50d ago
Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise
50d ago
Leveraging tails for adaptation
50d ago
Optimal Deterministic Multicalibration and Omniprediction
50d ago
Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks
51d ago
ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift
51d ago
Compact Geometric Representations of Hierarchies
51d ago
Toward Simultaneously Optimal Regret in U-Calibration
51d ago
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?
51d ago
Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies
51d ago
TimeLAVA: Learning-Agnostic Data Valuation for Time Series
51d ago
Kernel of Partition Paths: A Unified Representation for Tree Ensembles
51d ago
FOSC-X: An Extended Framework for Optimal Local Cuts and Non-Horizontal Cluster Selection from Clustering Hierarchies
51d ago
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
51d ago
Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning
51d ago
On Local Population-Risk Certificates
51d ago
Generalised Eigenvalue Geometry of Semantic Adversarial Attacks
51d ago
The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
51d ago
A Guide to Estimating Conditional Average Treatment Effects in Competing Risks Settings
51d ago
Fisher Width: A Geometric Measure of Complexity on Statistical Manifolds
51d ago
Bayesian Nonparametric Detection of Anomalies in Multivariate Functional Data
51d ago
Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction
51d ago
Mixed-Precision Communication-Avoiding SGD for Generalized Linear Models on GPUs
51d ago
Quantum Annealing Enhanced Reinforcement Learning for Accurate Remaining Useful Lifetime Prediction
51d ago
Another Look at Log-PCA for Probability Measures: A Dynamical Formulation and Statistical Convergence
52d ago
Tight $L_\infty$ Sample Complexity for Low-Degree and Sparse Boolean Polynomials
52d ago
Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty
52d ago
A Bayesian Boolean Matrix Factorization with Application to Copy Number Analysis in Cancer
52d ago
Geometrical fairness in graph neural networks
52d ago
Differential Privacy of Gaussian Process Posterior Sampling
52d ago
Fast Nonparametric Conditional Independence Testing via Two-Stage Regression
52d ago
Tensor-based second-order causal discovery
52d ago
A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise
52d ago
Finsler Geometry, Graph Neural Networks, and You
52d ago
Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization
52d ago
Uncertainty Quantification of Engineering Structures by Polynomial Chaos Expansion and Multivariate Active Learning
52d ago
Accelerated Convex Optimization via Hamiltonian Dynamics with Deterministic Integration Time
52d ago
Bayesian Poisson-Randomized Gamma Tensor Factorization with Application to International Trade Flows
52d ago
Kernel-Based Functional Balancing for Causal Inference with Compositional Treatments
52d ago
A Polyak-Ruppert Central Limit Theorem for SA-Adam with Momentum and Non-Convergent Adaptive Preconditioning
52d ago
Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy Validation
52d ago
Martingale Doppelg\"anger-Eval: An Identification Framework for Auditing Candlestick Understanding in Vision-Language Models
52d ago
Anytime-valid Optimal Policy Identification
52d ago
FoundCause: Causal Discovery with Latent Confounders from Observational Data
52d ago
Audited Conformal Prediction for Classification under Unknown Distribution Shift
53d ago
Conformal Candidate Certification for Offline Model-Based Optimization
53d ago
Finite Resources False Discovery Rate Control in Structured Hypothesis Spaces
53d ago
The Reverse Telescoping Coordinate System for Positive Definite Matrices: Geometry, Computation, and Generative Modeling
53d ago
Structured Nonparametric Variational Inference for Dependent Latent Modeling
53d ago
Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow
53d ago
Phase Transition in Convex Relaxations for Graph Alignment
53d ago
Information Gap and Feasibility-Aware Inference in Binomial Logistic Mixtures
53d ago
Stochastic trace estimation with tensor train random vectors
53d ago
Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data
53d ago
PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift
53d ago
Closing the Approximation Gap in Simulation-free Latent SDEs
53d ago
Generative Modeling on Metric Graphs via Neural Optimal Transport
53d ago
Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
53d ago
Attention is Just Another Name for Coupling?: A Fast-Slow ODE Perspective on Hierarchical Pretraining
53d ago
A nonparametric two-sample test using a parametric integral probability metric
53d ago
Sobolev Approximation by Fixed-Size Neural Networks with Arbitrary Accuracy
53d ago
Dynestyx: A Probabilistic Programming Library for Dynamical Systems
53d ago
Learning Topological Representations for Molecular Dynamics
53d ago
Bridging data-driven priors via the score function for posterior sampling -- Comparative review and experimental study
53d ago
LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models
54d ago
Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
54d ago
Adaptive Nucleus Truncation for Long-Form Reasoning
54d ago
A General Framework for Decision Trees via Bregman Divergences
54d ago
Geometric Domain Adaptation via Optimal Transport for Linear Regression in R^2
54d ago
Anytime-Valid Confirmation of Label-Shift Corrections
54d ago
Hybrid Uncertainty Sensitivity Analysis Based on the HSIC for High-Dimensional Responses with Aleatory--Epistemic Separation
54d ago
Gradient boosting for extremes: sampling theory and application to insurance
54d ago
Nonlocal Bayesian Modeling of Continuous Spatio-Temporal Dynamics
54d ago
Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias
54d ago
Cluster LOCO: Feature Importance For Interpreting Clusters
54d ago
A fully GPU-based workflow for building physics emulators of hypersonic flows
54d ago
Conformal calibration and look-elsewhere effect in anomaly detection for new-physics searches
54d ago
A Stationarity-and-Coupling Criterion for Training-Free Time-Lagged Spectral Embeddings of Multivariate Time Series
54d ago
Approximating Whittle-Matern Fields over Discretized Manifolds
54d ago
Controller-Augmented Hidden Markov Models: A Computational Framework for Constrained Sequential Inference
54d ago
Lyapunov-Based Sample Complexity Analysis for Weakly-Coupled MDPs
54d ago
Temperature transferable Machine Learned Coarse Grained model for proteins
54d ago
Operator Calculus for Population-Based Optimization: A Mean-Field Convergence Theory
54d ago
Local Coverage Governs Memorization in Diffusion Models
54d ago
Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency
57d ago
Epistemic Uncertainty Is Not the Reducible Kind
57d ago
Prediction-Powered Causal Inference by Automatic Debiased Machine Learning and Semi-Supervised Riesz Regression
57d ago
Robust State-Conditional Feature-Weighted Jump Models for Temporal Clustering
57d ago
ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization
57d ago
Simultaneous Latent Budget Trees for Stratified Classification
57d ago
Majority-of-Three is Optimal
57d ago
A Two-Parameter Weibull Framework for Diagnosing Transformer Weight Distributions
57d ago
Computationally tractable robust differentially private mean estimation
57d ago
Physics-Informed Neural Networks for Chemotherapy Pharmacokinetics: Benchmarking the Clinical Estimator and Exposing Parameter Identifiability
57d ago
How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?
57d ago
Two-Layer Linear Auto-Regressive Models Estimate Latent States
57d ago
A unified complexity bound for logconcave sampling
57d ago
On McDiarmid's Inequality under Dependence via Approximate Tensorization of Entropy
57d ago
Diffusion-Network Alignment: An Efficient Algorithm and Explicit Probability Bounds
57d ago
Reliability of Probabilistic Emulation of Physical Systems
57d ago
A Quadratic Order Reduction -- Gaussian Process Ordinary Differential Equation framework for the inference of Large Continuous Dynamical Systems
57d ago
Calibrating simplified vine copulas with a noise contrastive estimation approach
57d ago
Towards More General Control of Diffusion Models Using Jeffrey Guidance
57d ago
REMAL: Residual Equilibrium Manifold Active Learning for Surrogate-Based Multidisciplinary Design Analysis
57d ago
Annealed Entropic Allocation for Ranking and Selection
58d ago
Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records
58d ago
Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach
58d ago
Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation
58d ago
From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features
58d ago
Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence
58d ago
Fixed-Parameter Tractability of Private Synthetic Data Generation
58d ago
Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry
58d ago
GraphGP: Scalable Gaussian Processes with Vecchia's Approximation
58d ago
Signed Compression Progress on a Sealed Audit is Goodhart-Resistant
58d ago
The Power of Test-Time Training for Approximate Sampling
58d ago
CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
58d ago
Unbiased Derivative Estimation for Stationary Mean of Parameterized Markov chains
58d ago
Continuous biome representations from Earth observation embeddings
58d ago
Range-Aware Bayesian Optimization for Discovering Diverse Designs within Target Property Windows
58d ago
Tree-Structured Orthonormal Decomposition of the Aitchison Simplex
58d ago
Capacity-Constrained Online Convex Optimization with Delayed Feedback
58d ago
Time Series Analysis in Machine Learning
58d ago
Magnitude-Based Features for Multispecies Spatial Data
58d ago
Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers
58d ago
Convergence Rates for Neural-Network Estimation with Current-Status Data
59d ago
Robust Active Learning for Few-Shot Example Selection in Text-to-SQL
59d ago
Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising
59d ago
$k$-Nearest Neighbors in Gromov--Wasserstein Space
59d ago
Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin
59d ago
Human-AI Teaming Through the Lens of Calibration
59d ago
Range Penalization: Theoretical Insights with Applications in Federated Learning
59d ago
Generalized Conformal Predictive Systems Under Distributional Shifts
59d ago
It\^o maps for any-step SDEs
59d ago
Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models
59d ago
Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages
59d ago
Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection
59d ago
Integrating Local and Global Entropy for Uncertainty Quantification in LLMs
59d ago
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts
59d ago
Nonlinear Estimator: Dual Bayesian Affine Estimators for Parameter Learning
59d ago
Intrinsic Footpoint-invariant Riemannian Cross-covariance
59d ago
Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks
59d ago
A Mean-Field Analysis of Multi-Head Self-Attention under Cross-Entropy Training
59d ago
Advancing the State-of-the-Art in Empirical Privacy Auditing
59d ago
Deterministic Denominator Design for Localized Tamed Stochastic-Gradient Langevin Dynamics
59d ago
Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference
60d ago
Transfer learning for causal forest
60d ago
Identifiability and Estimation for Unlabeled Finite Mixtures under Marginal Independence
60d ago
Barycentric Projections of Optimal Transport Plans on Riemannian Manifolds
60d ago
Variational Proximal Policy Optimization
60d ago
Beyond Additivity: Causal Discovery in Location-Scale Noise Models with Hidden Variables
60d ago
Vector Space of Cycles
60d ago
MEC-Cox: Machine-Learning-Assisted Generalized Entropy Calibration for ATT Marginal Hazard-Ratio Estimation
60d ago
Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models
60d ago
LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry
60d ago
Improving the sharpness in neural network-based parametric post-processing of ensemble forecasts
60d ago
Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation
60d ago
Generalization in Nonlinear Least Squares via Learned Feature Geometry
60d ago
Estimate Collapsibility of Causal Effects in Completed Partial DAGs via Strong d-Convex Hulls
60d ago
Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees
60d ago
SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths
60d ago
Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting
60d ago
Boundary Variance Inflation Causes Acquisition Bias in Gaussian Processes
60d ago
Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connections
60d ago
MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport
60d ago
Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks
61d ago
Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods
61d ago
Empirical Transfer Operators and Finite-Sample Change Detection for Noisy Expanding Interval Maps
61d ago
The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces
61d ago
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments
61d ago
Deep Single-Index Fr\'echet Regression
61d ago
Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions
61d ago
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
61d ago
TorchKM: A GPU-Oriented Library for Kernel Learning and Model Selection
61d ago
The Sharp Phase Transition of Tyler's M-Estimator for Robust Subspace Recovery
61d ago
Constructing VAE Latent Spaces with Prescribed Topology
61d ago
Information-Theoretic Bounds for Sparse Covariance Estimation in the Vertical-Split Distributed Model
61d ago
Principal Component Analysis for Multivariate Extremes
61d ago
Theory of learning of high-dimensional controlled non-linear dynamical systems (I): models and methods
61d ago
Covariance Shrinkage via Stochastic Interpolation
61d ago
Online Pandora's Box for Contextual LLM Cascading
61d ago
Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting
61d ago
Network Recovery from Cascade Data: A Debiased Jacobian-Based Machine Learning Approach
61d ago
Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies
61d ago
Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication
61d ago
Central Description Length (CDL) Clustering Validation Index
64d ago
HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation
64d ago
Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic-Gradient Noise and Localizing Taming
64d ago
Harnessing Source Heterogeneity for Cluster-Structured Transfer Learning
64d ago
TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness
64d ago
Environment-Robust Representation Learning with Empirical Bayes
64d ago
Sparse Functional Singular Value Decomposition for Biclustering and Triclustering Longitudinal Data
64d ago
Conformal Risk-Averse Decision Making with Action Conditional Guarantee
64d ago
Finding Most Influential Sets
64d ago
EML-CD: Causal Mechanism Recovery via EML Symbolic Trees in Structure Learning
64d ago
Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples
64d ago
Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
64d ago
Effective Dimensionality as an Operator Invariant for Physics-Preserving Constraint Adaptation in Physics-Informed Neural Networks
64d ago
Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
64d ago
Anchor PCA
64d ago
Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applications
64d ago
Symmetric Divergence and Normalized Similarity: A Unified Topological Framework for Representation Analysis
64d ago
Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction
64d ago
Conformal Risk Sharing: Certified Cost Allocation with Participation Guarantees
64d ago
DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables
64d ago
Counterfactual Explanations for Deep Two-Sample Testing
65d ago
Finite-Iteration Local Dynamics and Warm Starts for Alternating Power Iteration in Spiked Tensor PCA
65d ago
REGAIN: REconciliation GAIN-driven Auxiliary Direction Learning
65d ago
Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks
65d ago
Flatness and Generalization: Learning Multi-Index Models with Homogeneous Neural Networks
65d ago
ReSGA: A Large Tail Risk Model for Learning Value-at-Risk and Expected Shortfall
65d ago
Bayesian learning for the stochastic shortest path problem
65d ago
Pseudospectral Bounds for Transient Amplification in Coupled Gradient Descent
65d ago
TPA-AD: A Two-Stage Pseudo Anomaly-Guided Method for Bearing Time-Series Anomaly Detection
65d ago
Variance Reduction for Heavy-Tailed Monetization Metrics in Ranking Experiments via Post-Stratification
65d ago
Low-rank Distributional Matrix Completion
65d ago
Exact Unlearning in Reinforcement Learning
65d ago
Edge of Stability Selectively Shapes Learning Across the Data Distribution
65d ago
Offline-to-Online Learning in Linear Bandits
65d ago
Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries
65d ago
When Do Fewer Coordinates Suffice in DP-SGD?
65d ago
Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD
65d ago
The price of multi-group transductive learning
65d ago
When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks
65d ago
Global Sketch-Based Watermarking for Diffusion Language Models
65d ago
Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery
66d ago
Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics
66d ago
State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation
66d ago
ScoreStop: Gradient-based early stopping using functional score tests
66d ago
Scalable Derivative Gaussian Processes via Exact Gradient Reduction
66d ago
Trajectory-Aware Node Contributions and the Limits of Static Controllability
66d ago
An Asymptotic Theory of Chain-of-Thought in In-Context Learning
66d ago
Hierarchies of Calibration: Classification meets Regression
66d ago
Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification
66d ago
A Robust Optimization Approach to Sparse Principal Component Analysis
66d ago
Few-Shot Prediction for Pulsar Noise with Long Short-Term Memory Network
66d ago
Set-Preserving Calibration from Conformal P-Values to E-Values
66d ago
Resource-Constrained Adaptive Inference for Sequential Pricing
66d ago
A Quantitative Approximation Framework for Flow Distillation in Diffusion Models
66d ago
Privacy-Robust Incrementality Measurement for Advertising Systems under Signal Loss
66d ago
Rashomon-Seeded Annealing for Robust Bayesian Inference in Factorial Designs
66d ago
Recovering Direct Price Effects of Environmental Amenities in Housing Markets: Regression and Causal Machine Learning Model Assessment with Empirical Monte Carlo Simulation
66d ago
Neural Posterior Estimation for Stochastic Epidemic Models Using Final Outcome Data
66d ago
Neural Networks Provably Learn Spectral Representations for Group Composition
66d ago
A Fast Screening Approach for High-dimensional Outcomes and High-dimensional Predictors
66d ago
Interpreting FCDNNs via RG on Exponential Family
67d ago
Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach
67d ago
Is Zero-Shot Super-Resolution Possible in Operator Learning?
67d ago
ERICA: Quantifying Replicability of Cluster Analysis
67d ago
Riemannian Stochastic Optimization for Sufficient Dimension Reduction
67d ago
Parameter-Free and Group Conditional Online Conformal Prediction
67d ago
Spectra-Guided Neural Tucker Factorization
67d ago
Taming the Loss Landscape of PINNs with Noisy Feynman-Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds
67d ago
On Median of Incomplete U-Statistics
67d ago
Statistical Testing on Directed Graphs by Surrogate Data Generation
67d ago
Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifiers
67d ago
Bandit Simulation for Average Reward Inference
67d ago
Efficient Synthetic Network Generation via Latent Embedding Reconstruction
67d ago
Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates
67d ago
Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces
67d ago
Distribution-free changepoint localization after sequential change detection
67d ago
On the Uncertainty Quantification Ability of Tabular Foundation Models
67d ago
Computation-Aware Kalman Filtering with Model Selection for Neural Dynamics
67d ago
Self-Regulating Annealing in Heavy-Tailed Diffusion Models
67d ago
Provable Data Scaling Law for Meta Learning via Complexity Minimization
67d ago
Improved Distribution Estimation in $\ell_\infty$
68d ago
Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles
68d ago
Is the Last Layer Sufficient for Uncertainty Quantification?
68d ago
Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
68d ago
Hedging on the Frontier: Learning New Tasks with Few Samples
68d ago
Routing on the Stiefel Manifold: When Does Adaptive Subspace Selection Help for Cross-Domain EEG Decoding?
68d ago
Free energy Estimation on Any State Space
68d ago
Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks
68d ago
Memory by Design: Probabilistic Sequence Layers
68d ago
Correcting Split Selection in Online Decision Trees via Anytime-Valid Inference
68d ago
Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
68d ago
Log-Ratio Propagation on the Simplex: A Theory of Cellwise Contamination for Compositional Data
68d ago
Calibrated Preference Learning: The Case of Label Ranking
68d ago
Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics
68d ago
Benchmark of Likelihood-Free Inference Methods based on Neural and Optimal Transport Approaches
68d ago
True Self-Avoiding Walk for Accelerating Markov-Chain Monte Carlo Integration
68d ago
Active Timepoint Selection for Learning Measure-Valued Trajectories
68d ago
SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMs
68d ago
Moment-Based Inference for Regression with Latent Dirichlet Covariates
68d ago
Kalimati Vegetable Price Index Forecasting with a Momentum Corrected Online Stacking Ensemble
68d ago
Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions
71d ago
Anytime-Valid Federated Conformal RAG for LLM Swarms
71d ago
Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research
71d ago
Deep Optimal Individualized Treatment Rules for Bivariate Survival Outcomes via Adaptive Prediction-Powered Learning
71d ago
Matching Rates and Optimal Allocation for Federated Probe-Logit Distillation under Heterogeneous Bandwidth Budgets
71d ago
Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data
71d ago
Instance-dependent Stochastic Lipschitz bandit
71d ago
Joint Model and Data Sparsification via the Marginal Likelihood
71d ago
Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
71d ago
Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks
71d ago
Wasserstein Contraction of Coordinate Ascent Variational Inference
71d ago
Leave a Window Out: Modifying the Jackknife for Predictive Inference in Time Series
71d ago
Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
71d ago
Saddle Networks: Structure-Preserving Architectures for Convex-Concave Functions
71d ago
Conf-Gen: Conformal Uncertainty Quantification for Generative Models
71d ago
Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
71d ago
Optimal Gap-Dependent Regret for Private Stochastic Decision-Theoretic Online Learning
71d ago
Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
71d ago
Bayesian Multiplicity Correction in the Probabilistic Forward Stepwise Framework
71d ago
Causal Label Recovery in Payment Networks
71d ago
Calibrated Inference for the Conditional Average Treatment Effect in the Few-Placebo Regime via Gaussian Processes
72d ago
Stop Suppressing the Tail: Causal Inference for Extreme Events
72d ago
Iterative Causal Discovery: Per-Edge Impossibility Certificates, Tier-Aware Oracle Queries, and the $1+K$ Lower Bound
72d ago
Triangular-Reference Schr\"odinger Bridges for Time Series Generation
72d ago
Identifiable Bayesian Deep Generative Copulas with Unknown Layer Widths for Data with Arbitrary Marginal Distributions
72d ago
Semiparametrically Efficient Inference for Kernel Measures of Noise Heterogeneity
72d ago
Accelerating Reinforcement Learning Training Using Simulation Surrogate Models
72d ago
Evolving and Detecting Multi-Turn Deception using Geometric Signatures
72d ago
Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning
72d ago
Soft Specialists: $\alpha$-R\'enyi Ensembles for Uncertainty-Aware LLM Post-Training
72d ago
Learning to target with network interference
72d ago
Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
72d ago
Deep Neural Network Training as Random Effects: An Optimization-Inference Duality
72d ago
The conditional-mean barrier: From deterministic regression to conditional distribution learning
72d ago
Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings
72d ago
Counterfactually Fair Regression via Optimal Transport
72d ago
Insurance Pricing Optimization via Off-Policy Evaluation
72d ago
Decision-focused learning for optimal PV-Battery scheduling
72d ago
Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation
72d ago
Bridging Maximum Likelihood and Optimal Transport for Efficient Inference and Model Selection in Stochastic Block Models
72d ago
Learning Nonlinear Factor Models with Unknown Monotone Links from Incomplete and Noisy Data
73d ago
Beyond Differences: Doubly Robust Meta-Learners for Ratio-Based Treatment Effects
73d ago
When Does LeJEPA Learn a World Model?
73d ago
CART Random Forests as Sequential Allocation over Random Opportunity Sets: A Stochastic-Control Theory of Ensemble Risk
73d ago
Transformers Can Learn Posterior Predictive Distributions In-Context
73d ago
Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks
73d ago
Constrained Bayesian Experimental Design via Online Planning
73d ago
Causal Representation Learning for Generalisable Recommendation
73d ago
Gaussian Process-based learning with new MCMC-based implementation of Wishart prior on correlation matrix
73d ago
Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models
73d ago
From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD
73d ago
A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning
73d ago
Fast Convergence of Policy Regret in Learning Stochastic Optimal Control
73d ago
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
73d ago
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
73d ago
Function-Valued Causal Influence in Nonlinear Time Series
73d ago
Confounder Detection via Treatment Intent: A New Observational Study Design
73d ago
Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing
73d ago
Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift
73d ago
Sample Complexity of Policy Gradient for Log-Growth Control
73d ago
Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs
74d ago
Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines
74d ago
Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination
74d ago
MEDAL: Manifold Embedding Distillation via Autoencoder Learning
74d ago
Multicalibration Boosting: Theory, Convergence, and Transferability
74d ago
Clustering based on Stochastic Dominance with application for risk averters and risk seekers
74d ago
Affinity Graph Connectivity in Convex Clustering
74d ago
How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis
74d ago
Estimating Mixture Distributions via Stochastic Mirror Descent
74d ago
Counterfactually Safe Reinforcement Learning
74d ago
Nystr\"om Kernel Stein Discrepancy Tests
74d ago
Choosing Online Experiment Designs under Interference in Ads, Recommendations, and Member-Experience Systems
74d ago
Learning manifold diffusion semigroups from graph transition matrices
74d ago
Mean-Shift PCA by Knockoff Mean
74d ago
Guided Flow Matching for Forward and Inverse PDE Problems with Sparse Observations: Algorithm and Theory
74d ago
From DPPs to $k$-DPPs: identifiability analysis via spectral decomposition
74d ago
Rao-Blackwellized Score Matching on Manifolds
74d ago
Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent
74d ago
Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification
74d ago
Learning Sparse Compositional Functions with Norm-Constrained Neural Networks
74d ago
Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation
75d ago
KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
75d ago
LLM Sparsity Prior for Robust Feature Selection
75d ago
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
75d ago
Coupled Training with Privileged Information and Unlabeled Data
75d ago
Concomitant DAG Learning: On the Roles of Noise Adaptivity, Sparsity, and Non-negativity
75d ago
Asymmetric Scaling Laws from Sparse Features
75d ago
Dirichlet-Based Monte Carlo Dropout for Uncertainty Estimation in Neural Networks
75d ago
Learning Kernel-Based MDPs from Episodic Preferential Feedback
75d ago
Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
75d ago
On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy
75d ago
Symbolic Density Estimation for Discrete Distributions
75d ago
Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
75d ago
Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity
75d ago
Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning
75d ago
Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics
75d ago
HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation
75d ago
Anytime Training with Schedule-Free Spectral Optimization
75d ago
Mode-Shape Expansion Using Physics-Constrained Gaussian Process Regression
75d ago
Robust OT-Guided Generative Residual Domain Adaptation for Bike-Sharing Demand Prediction under Temporal Domain Shift
75d ago
Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks
78d ago
Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions
78d ago
Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling
78d ago
Support-aware offline policy selection for advertising marketplaces
78d ago
Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
78d ago
From Betting to Empirical Bernstein LIL
78d ago
Departure from Regularity: Degree Heterogeneity and Eigengap as the Structural Drivers of ASE-LSE Latent Subspace Disagreement
78d ago
Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions
78d ago
A Martingale Kernel Independence Test
78d ago
Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
78d ago
Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data
78d ago
The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity
78d ago
Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery
78d ago
Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
78d ago
Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
78d ago
Distribution-free root cause analysis
78d ago
Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
78d ago
Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective
78d ago
On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
78d ago
MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation
78d ago
Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity
79d ago
Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models
79d ago
Contradiction Graphs Determine VC Dimension
79d ago
Sample Complexity of Transfer Learning: An Optimal Transport Approach
79d ago
Spectral bandits for smooth graph functions with applications in recommender systems
79d ago
Group-Aware Matrix Estimation and Latent Subspace Recovery
79d ago
Conditioning Gaussian Processes on Almost Anything
79d ago
A Rigorous, Tractable Measure of Model Complexity
79d ago
Federated LoRA Fine-Tuning for LLMs via Collaborative Alignment
79d ago
Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference
79d ago
Large-Step Training Dynamics of a Two-Factor Linear Transformer Model
79d ago
Semiparametric Efficient Bilevel Gradient Estimation
79d ago
Memorisation, convergence and generalisation in generative models
79d ago
A Differentiable Measure of Algebraic Complexity: Provably Exact Discovery of Group Structures
79d ago
Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity
79d ago
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
79d ago
Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels
79d ago
Score-Based Causal Discovery of Latent Variable Causal Models
79d ago
Understanding Deterioration Random Effects for Causal Discovery in Infrastructure Management
79d ago
CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support
79d ago
Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors
80d ago
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
80d ago
Conformal Prediction via Transported Beta Laws
80d ago
Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming
80d ago
Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection
80d ago
Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration
80d ago
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
80d ago
Factor Augmented High-Dimensional SGD
80d ago
A Unified Framework for Structure-Aware Clustering and Heterogeneous Causal Graph Learning
80d ago
Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian
80d ago
Density-Ratio Losses for Post-Hoc Learning to Defer
80d ago
Posterior Contraction of L\'evy Adaptive B-spline Regression in Besov Spaces
80d ago
Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation
80d ago
Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data
80d ago
Probabilistic Multivariate Time Series Forecasting with Diffusion Copulas
80d ago
Tail Annealing for Heavy-Tailed Flow Matching
80d ago
Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation
80d ago
Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization
80d ago
Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
80d ago
When Individually Calibrated Models Become Collectively Miscalibrated
80d ago
Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
81d ago
StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow
81d ago
Isotonic Survival Regression: Calibrated Survival Distributions from Deep Cox Models
81d ago
Prediction-Intervention Games and Invariant Sets
81d ago
HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations
81d ago
A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
81d ago
CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series
81d ago
Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations
81d ago
Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and Safety
81d ago
Sample efficient inductive matrix completion with noise and inexact side information
81d ago
On Gaussian approximation for entropy-regularized Q-learning with function approximation
81d ago
Online Conformal Prediction for Non-Exchangeable Panel Data
81d ago
How does feature learning reshape the function space?
81d ago
StatQAT: Statistical Quantizer Optimization for Deep Networks
81d ago
Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
81d ago
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
81d ago
A data-driven Fourier-mixture neural-network method for density estimation
81d ago
A note on connections between the F\"ollmer process and the denoising diffusion probabilistic model
81d ago
Wasserstein bounds for denoising diffusion probabilistic models via the F\"ollmer process
81d ago
Canonical Regularisation of Wide Feature-Learning Neural Networks
81d ago
On Kernel Eigen-alignments of KRR: Reconstruction and Generalization
82d ago
Harnessing Unimodality in Semiparametric Contextual Pricing via Oracle Price Map Learning
82d ago
MaxSketch: Robust Distinct Counting in Streams via Random Projections
82d ago
Pessimistic Risk-Aware Policy Learning in Contextual Bandits
82d ago
$\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
82d ago
Unsupervised Domain Shift Detection with Interpretable Subspace Attribution
82d ago
Testing properties of trees in graphical models with covariance queries
82d ago
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
82d ago
A numerical study into neural network surrogate model performance for uncertainty propagation
82d ago
Skew-adaptive conformal prediction
82d ago
A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature
82d ago
How Data Augmentation Shapes Neural Representations
82d ago
Proposal-Guided Greedy Surrogate Refinement for PDE-Driven High-Dimensional Rare-Event Estimation
82d ago
Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
82d ago
$\phi$-Balancing for Mixture-of-Experts Training
82d ago
Reasoning Models Don't Just Think Longer, They Move Differently
82d ago
Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
82d ago
Improving the Efficiency of Subgroup Analysis in Randomized Controlled Trials with TMLE
82d ago
SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference
82d ago
Leveraging heterogeneity for identifiability: Bayesian order-based learning of multiple DAGs
82d ago
AIS: Adaptive Importance Sampling for Quantized RL
85d ago
Covariance-aware sampling for Diffusion Models
85d ago
A Survey on Data-Dependent Worst-Case Generalization Bounds
85d ago
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
85d ago
A Regret Perspective on Online Multiple Testing
85d ago
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
85d ago
To discretize continually: Mean shift interacting particle systems for Bayesian inference
85d ago
On the Burden of Achieving Fairness in Conformal Prediction
85d ago
Training-Free Generative Sampling via Moment-Matched Score Smoothing
85d ago
Large Dimensional Kernel Ridge Regression: Extending to Product Kernels
85d ago
Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
85d ago
K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles
85d ago
Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models
85d ago
From Data to Action: Accelerating Refinery Optimization with AI
85d ago
Logging Policy Design for Off-Policy Evaluation
85d ago
RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution
85d ago
Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling
85d ago
Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm
85d ago
TabPFN-3: Technical Report
85d ago
Finite-size scaling of hetero-associative retrieval in continuous-signal-driven Ising spin systems
85d ago
Online Conformal Prediction: Enforcing monotonicity via Online Optimization
86d ago
A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention
86d ago
ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
86d ago
Robust Sequential Experimental Design for A/B Testing
86d ago
The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
86d ago
When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
86d ago
Coreset-Induced Conditional Velocity Flow Matching
86d ago
Adaptive Kernel Density Estimation with Pre-training
86d ago
State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
86d ago
Amortized Neural Clustering of Time Series based on Statistical Features
86d ago
On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods
86d ago
Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process
86d ago
Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
86d ago
Coupling-Informed Transport Maps for Bayesian Filtering in Nonlinear Dynamical Systems
86d ago
LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information
86d ago
The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
86d ago
Learning Perturbations to Extrapolate Your LLM
86d ago
On the Limits of Latent Reuse in Diffusion Models
86d ago
Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models
86d ago
Causal Learning with the Invariance Principle
86d ago
Uniform Scaling Limits in AdamW-Trained Transformers
87d ago
Interpretable Machine Learning for Spatial Science: A Lie-Algebraic Kernel for Rotationally Anisotropic Gaussian Processes
87d ago
Adaptive Policy Learning Under Unknown Network Interference
87d ago
Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors
87d ago
Post-ADC Inference: Valid Inference After Active Data Collection
87d ago
Exact Stiefel Optimization for Probabilistic PLS: Closed-Form Updates, Error Bounds, and Calibrated Uncertainty
87d ago
Learning U-Statistics with Active Inference
87d ago
Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
87d ago
Minimax Rates and Spectral Distillation for Tree Ensembles
87d ago
Variance-aware Reward Modeling with Anchor Guidance
87d ago
Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions
87d ago
Information-Theoretic Generalization Bounds for Sequential Decision Making
87d ago
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
87d ago
Optimal Policy Learning under Budget and Coverage Constraints
87d ago
Online Learning-to-Defer with Varying Experts
87d ago
Multi-Variable Conformal Prediction: Optimizing Prediction Sets without Data Splitting
87d ago
Model-based Bootstrap of Controlled Markov Chains
87d ago
Testing General Relativity Through Gravitational Wave Classification: A Convolutional Neural Network Framework
87d ago
Sensor Design for Accuracy-Bounded Estimation via Maximum-Entropy Likelihood Synthesis
87d ago
Variational predictive resampling
87d ago
Decentralized Conformal Novelty Detection via Quantized Model Exchange
88d ago
Active Multiple-Prediction-Powered Inference
88d ago
Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
88d ago
Sliced Inner Product Gromov-Wasserstein Distances
88d ago
Learnability and Competition in High-Dimensional Multi-Component ICA
88d ago
CONTRA: Conformal Prediction Region via Normalizing Flow Transformation
88d ago
Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems
88d ago
Measuring and Decomposing Mode Separation via the Canonical Diffusion
88d ago
Learning Theory of Transformers: Local-to-Global Approximation via Softmax Partition of Unity
88d ago
Tight Generalization Bounds for Noiseless Inverse Optimization
88d ago
Survey-aware Machine Learning: A Guideline for Valid Population Health Inference based on Scoping Review
88d ago
Optimality of Sub-network Laplace Approximations: New Results and Methods
88d ago
Optimal Regret for Single Index Bandits
88d ago
Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow
88d ago
Empirical Bayes 1-bit matrix completion
88d ago
Metropolis-Adjusted Diffusion Models
88d ago
Learning stochastic multiscale models through normalizing flows
88d ago
Supercharging Bayesian Inference with Reliable AI-Informed Priors
88d ago
Unified Approach for Weakly Supervised Multicalibration
88d ago
Federated Language Models Under Bandwidth Budgets: Distillation Rates and Conformal Coverage
88d ago
How Does Attention Help? Insights from Random Matrices on Signal Recovery from Sequence Models
89d ago
One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators
89d ago
Kernel Selection is Model Selection: A Unified Complexity-Penalized Approach for MMD Two-Sample Tests
89d ago
Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions
89d ago
A Differentiable Bayesian Relaxation for Latent Partial-Order Inference
89d ago
BGM-IV: an AI-powered Bayesian generative modeling approach for instrumental variable analysis
89d ago
An Interpretable and Scalable Framework for Evaluating Large Language Models
89d ago
Causal EpiNets: Precision-corrected Bounds on Individual Treatment Effects using Epistemic Neural Networks
89d ago
Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
89d ago
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
89d ago
Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examples
89d ago
Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
89d ago
A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning
89d ago
Reliable Chain-of-Thought via Prefix Consistency
89d ago
Debiased Counterfactual Generation via Flow Matching from Observations
89d ago
TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
89d ago
Flow Matching for Count Data
89d ago
Expectation-Maximization as a Spectrally Governed Relaxation Flow
89d ago
Characterizing and Correcting Effective Target Shift in Online Learning
89d ago
Consistency Regularised Gradient Flows for Inverse Problems
89d ago
Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
92d ago
Forecasting Oncology Demand Trends with Boosting-Based Bayesian Conjugate Models
92d ago
Estimating Implicit Regularization in Deep Learning
92d ago
Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation
92d ago
Permutation-preserving Functions and Neural Vecchia Covariance Kernels
92d ago
Relaxed Sparsest-Permutation Formulation for Causal Discovery at Scale
92d ago
In-Context Positive-Unlabeled Learning
92d ago
Variational Smoothing and Inference for SDEs from Sparse Data with Dynamic Neural Flows
92d ago
Spherical Flows for Sampling Categorical Data
92d ago
Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization
92d ago
Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring and FFCI Testing in Mixed Data
92d ago
Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
92d ago
Ratio-based Loss Functions
92d ago
CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency
92d ago
Tuning Derivatives for Causal Fairness in Machine Learning
92d ago
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
92d ago
TabCF: Distributional Control Function Estimation with Tabular Foundation Models
92d ago
Gaussian mixture models in Hilbert spaces via kernel methods
92d ago
Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective
92d ago
When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination
92d ago
A Consistency-Centric Approach to Set-Based Optimization with Multiple Models of Unranked Fidelity
93d ago
Heterogeneous Ordinal Structure Learning with Bayesian Nonparametric Complexity Discovery
93d ago
Entropic Riemannian Neural Optimal Transport
93d ago
Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
93d ago
Perturbation is All You Need for Extrapolating Language Models
93d ago
Multiscale Euclidean Network Trajectories: Second-Moment Geometry, Attribution, and Change Points
93d ago
Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift
93d ago
Scalable inference of spatial regions and temporal signatures from time series
93d ago
Hypergraph Generation via Structured Stochastic Diffusion
93d ago
Proximal Projection for Doubly Sparse Regularized Models
93d ago
Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
93d ago
Bayesian Optimization in Linear Time
93d ago
BOOOM: Loss-Function-Agnostic Black-Box Optimization over Orthonormal Manifolds for Machine Learning and Statistical Inference
93d ago
Explaining and Preventing Alignment Collapse in Iterative RLHF
93d ago
A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning
93d ago
Symbolic Regression via Neural Networks
93d ago
Causal discovery under mean independence and linearity
93d ago
Augmented transfer regression learning for completely missing covariates
93d ago
FL-Sailer: Efficient and Privacy-Preserving Federated Learning for Scalable Single-Cell Epigenetic Data Analysis via Adaptive Sampling
93d ago
From Video-to-PDE: Data-Driven Discovery of Nonlinear Dye Plume Dynamics
93d ago
Dynamic Vine Copulas: Detecting and Quantifying Time-Varying Higher-Order Interactions
94d ago
Conformalized Percentile Interval: Finite Sample Validity and Improved Conditional Performance
94d ago
Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancy
94d ago
Partial Effective Information Decomposition for Synergistic Causality
94d ago
On the Spectral Structure and Objective Equivalence of Orthogonal Multilabel Fisher Discriminants
94d ago
Imbalanced Classification under Capacity Constraints
94d ago
Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity
94d ago
Stochastic Schr\"odinger Diffusion Models for Pure-State Ensemble Generation
94d ago
Free Decompression with Algebraic Spectral Curves
94d ago
Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification
94d ago
Tempered Guided Diffusion
94d ago
Predicting missing values: A good idea?
94d ago
Low Rank Tensor Completion via Adaptive ADMM
94d ago
Training-Free Probabilistic Time-Series Forecasting with Conformal Seasonal Pools
94d ago
The Manokhin Probability Matrix: A Diagnostic Framework for Classifier Probability Quality
94d ago
Conditional Diffusion Sampling
94d ago
Analysis and Explainability of LLMs Via Evolutionary Methods
94d ago
Disease Is a Spectral Perturbation
94d ago
ISAAC: Auditing Causal Reasoning in Deep Models for Drug-Target Interaction
94d ago
Joint Energy Management and Coordinated AIGC Workload Scheduling for Distributed Data Centers: A Diffusion-Aided Reward Shaping Approach
94d ago
Mean Testing under Truncation beyond Gaussian
95d ago
Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation
95d ago
Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression
95d ago
PRCD-MAP: Learning How Much to Trust Imperfect Priors in Causal Discovery
95d ago
Missingness-aware Data Imputation via AI-powered Bayesian Generative Modeling
95d ago
Distributional Causal Mediation via Conditional Generative Modeling
95d ago
A Semi-Supervised Kernel Two-Sample Test
95d ago
Stable Blanket with Hidden Variables and Cycles
95d ago
Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality
95d ago
Extrapolation in Statistical Learning with Extreme Value Theory
95d ago
MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
95d ago
The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy
95d ago
Measuring Differences between Conditional Distributions using Kernel Embeddings
95d ago
Active multiple matrix completion with adaptive confidence sets
95d ago
Middle-mile logistics through the lens of goal-conditioned reinforcement learning
95d ago
Black-box optimization of noisy functions with unknown smoothness
95d ago
Online Generalised Predictive Coding
95d ago
ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data
95d ago
Random-Effects Algorithm for Random Objects in Metric Spaces
95d ago
An Efficient Spatial Branch-and-Bound Algorithm for Global Optimization of Gaussian Process Posterior Mean Functions
95d ago
Adaptive Norm-Based Regularization for Neural Networks
96d ago
SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contamination
96d ago
A unified perspective on fine-tuning and sampling with diffusion and flow models
96d ago
Information-geometric adaptive sampling for graph diffusion
96d ago
Gradient Regularized Newton Boosting Trees with Global Convergence
96d ago
Adaptive Querying with AI Persona Priors
96d ago
Decentralized Proximal Stochastic Gradient Langevin Dynamics
96d ago
Mean-Field Path-Integral Diffusion: From Samples to Interacting Agents
96d ago
Smart Ensemble Learning Framework for Predicting Groundwater Heavy Metal Pollution
96d ago
Provable and scalable quantum Gaussian processes for quantum learning
96d ago
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
96d ago
Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback
96d ago
OTSS: Output-Targeted Soft Segmentation for Contextual Decision-Weight Learning
96d ago
A Dirac-Frenkel-Onsager principle: Instantaneous residual minimization with gauge momentum for nonlinear parametrizations of PDE solutions
96d ago
Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity
96d ago
M-CaStLe: Uncovering Local Causal Structures in Multivariate Space-Time Gridded Data
96d ago
Optimal Spatio-Temporal Decoupling for Bayesian Conformal Prediction
96d ago
Concentration and Calibration in Predictive Bayesian Inference
96d ago
Batch Normalization for Neural Networks on Complex Domains
96d ago
Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation
96d ago
1351 loaded
ML
Machine learning : nature.com subject feeds
1d ago · 20 items
AI-based augmentation of oncology clinical trials
1d ago
Oncology clinical trials are often characterized by slow accrual, high failure rates and limited generalizability, reflecting both biological complexity and operational inefficiencies. Advances in artificial intelligence (AI) — enabled by l...
Inference of tumor spatial habitats
2d ago
Nature Methods - Inference of tumor spatial habitats
AI agents are checking the scientific literature — and spotting decades-old errors
2d ago
The technology is proving adept at finding faults in decades-old papers and reference databases.
The Virtual Tissues foundation model resolves spatial proteomics across scales
3d ago
Spatial proteomics technologies have transformed our understanding of complex tissue architecture in cancer but present unique challenges for computational analysis1. Each study uses a different marker panel and protocol, and most methods a...
Privacy risks from medical AI tools are not shared equally
4d ago
Privacy attacks can reveal whether someone’s medical data was used to train an AI model. People who differ from the majority are the most vulnerable to such attacks.
Divergent impacts of explainable AI for dermatological diagnosis on clinicians versus lay people
4d ago
Artificial intelligence (AI) is increasingly permeating healthcare, from serving as a physician assistant to powering consumer applications. The opacity of AI algorithms makes the ability of humans to interact with AI algorithms challenging...
Automatic report-based assessment of radiology-pathology concordance in surgical patients using BERT and DPCNN
5d ago
Assessing radiology-pathology concordance is important for retrospective audit, educational feedback, and quality assurance in radiology practice. However, automated concordance assessment remains challenging because of imbalanced data and ...
Want to get more from AI? Treat every prompt like an experiment
5d ago
Taking a scientific approach to artificial-intelligence queries makes every output a result to be checked, says James Dewar. Here are ten tips for doing it right.
A foundation model for sleep-based risk stratification and clinical outcomes
5d ago
Clinical sleep studies capture multiple physiologic signals, yet interpretation is often reduced to single summary measures of limited prognostic value, such as the apnea–hypopnea index. We present a foundation model that learns rich repres...
Dynamic feature pyramid network for real-time gesture recognition
7d ago
Effective gesture recognition in Virtual Reality (VR) and Augmented Reality (AR) faces significant challenges from varying hand angles, postures, and complex backgrounds, limiting real-time application potential. This paper proposes the Dyn...
Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer
7d ago
Unify learns cellular evolution with universal multimodal embeddings
8d ago
Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms
8d ago
Learning from routine health system data builds better neuroimaging AI models
8d ago
A machine learning framework for predicting and modulating condition-dependent protein phase separation
8d ago
Scientists using LLMs will ‘do more, less well’, modelling study predicts
8d ago
Continual integration of single-cell multimodal data with MIRACLE
8d ago
CellTune: an integrative software for accurate cell classification in spatial proteomics
8d ago
Structural alignments to design functional RNAs
9d ago
An embedding-based framework enables statistical testing of gene-set function hypotheses inferred by large language models
9d ago
20 loaded
AM
Apple Machine Learning Research
1d ago · 10 items
Scaling Categorical Flow Maps
1d ago
Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling…
Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models
1d ago
Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks…
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
1d ago
Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational…
Locking Pretrained Weights via Deep Low-Rank Residual Distillation
2d ago
The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by…
DeepAmbigQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness
2d ago
Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often…
Taming Outlier Tokens in Diffusion Transformers
3d ago
We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can…
Understanding Alignment in Multimodal LLMs: A Comprehensive Study
5d ago
Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in…
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP’s kNN Graph
9d ago
While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely…
MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization
9d ago
To operate effectively across diverse contexts, robots must not only perform manipulation tasks accurately but also adapt how their actions…
Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers
11d ago
Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple’s…
GD
Google DeepMind News
1d ago · 20 items
WeatherNext: AI model achieves breakthrough in forecasting cyclones
1d ago
WeatherNext enables accurate cyclone forecasts that can give an extra day of warning. Now we are open sourcing the model.
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration
8d ago
Gemini Robotics ER 2 is a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic applications.
We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control
9d ago
Our newest music generation model, Lyria 3.5, delivers significant advancements across musicality, lyrics, and vocal quality, empowering you to craft richer tracks. We’r…
Gemini Robotics 2 brings whole body intelligence to robots
10d ago
From feet to fingertips — we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.
Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission
16d ago
Google is committing $40 million in AI tokens and cloud credits to support the DOE’s Genesis Mission and accelerate groundbreaking scientific discovery.
Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
17d ago
We’re introducing new Gemini models, including Gemini 3.6 Flash, 3.5 Flash-Lite and 3.5 Flash Cyber.
Introducing Gemini 3.5 Flash Cyber
21d ago
Google introduces Gemini 3.5 Flash Cyber to help defenders find, validate, and patch software vulnerabilities quickly and efficiently.
Our approach to bioresilience
23d ago
Google DeepMind and Isomorphic Labs approach to bioresilience, using AI models to support prevention, detection and response.
Empowering India’s next generation of innovators with ATL Saathi
25d ago
Atal Innovation Mission launches ATL Saathi, a Gemini powered AI assistant empowering India's educators to nurture the next generation of innovators.
Google DeepMind and A24 announce first-of-its-kind research partnership
35d ago
Today, Google DeepMind and A24 are announcing a first-of-its-kind partnership focused on research. The collaboration pairs a world-leading research lab with the industry…
Start building with Nano Banana 2 Lite and Gemini Omni Flash
38d ago
Introducing computer use in Gemini 3.5 Flash
44d ago
Unlocking UK house-building with AI-accelerated planning
52d ago
Securing the future of AI agents
52d ago
DiffusionGemma: 4x faster text generation
58d ago
Investing in multi-agent AI safety research
59d ago
Fluid, natural voice translation with Gemini 3.5 Live Translate
59d ago
Introducing Gemma 4 12B: a unified, encoder-free multimodal model
59d ago
Powering the future of robotics in Europe
59d ago
Measuring the impact of learning with AI in Sierra Leone and beyond
60d ago
20 loaded
AS
Amazon Science homepage
2d ago · 20 items
34 Amazon Research Awards Build on Trainium recipients announced
2d ago
Amazon announces 34 recipients of the Build on Trainium program, a $110 million credit initiative supporting AI research at 30 universities including Stanford, UC Berkeley, UIUC, UCLA, CMU, and MIT, with a focus on Responsible AI.
How controllers from industrial machinery can coordinate multitask machine learning
8d ago
Instead of compromising among parameter updates dictated by different training objectives, ControlG allocates computational capacity to objectives sequentially and dynamically.
A new benchmark for evaluating patient-facing health AI agents
9d ago
PatientAgentBench generates a synthetic patient health record, a realistic clinical vignette, and a patient agent that converses with the AI system under evaluation, to capture what a patient-facing agent actually has to do.
Amazon is investing in the Lean Focused Research Organization
13d ago
As AI agents take on higher-stakes decisions, Lean programming language makes it possible to mathematically prove they will behave safely.
Amazon and University of Michigan give robots a sense of touch
28d ago
Amazon and University of Michigan researchers developed a physics-based tactile simulator that teaches robots dexterous manipulation skills in simulation with a 93% real-world success rate — no fine-tuning required.
Capturing token IDs during agentic interactions for better reinforcement learning
29d ago
A new Rust proxy called Turnstile sits between the model backend and the agent harness to capture information lost in mere text transcripts.
How Amazon tracks carbon intensity across its operations
37d ago
Amazon is developing precise, sector-specific approaches to measuring decarbonization progress — starting with emissions per unit shipped.
The fuel of the future is already here: Why TRISO matters
44d ago
Each TRISO particle is a millimeter-wide containment system — engineered to withstand extreme temperatures and retain fission products for thousands of years. Here's how this advanced fuel technology works and why Amazon is investing in it ...
EC2’s formally verified “isolation engine” provides mathematical assurance of virtual-machine isolation
58d ago
330,000 lines of machine-checked proofs in Isabelle/HOL verify that the Nitro Isolation Engine correctly enforces confidentiality, integrity, and memory safety between EC2 virtual machines on Graviton5.
Graviton5’s improved design increases speed and energy efficiency — beyond Moore’s law
58d ago
Graviton5's four-chiplet architecture, custom die-to-die connectivity, three-nanometer process, and 192 megabytes of L3 cache deliver up to 35% faster performance for web applications and ML inference.
Real-world grounding in agentic AI
60d ago
Bridging intent and execution in agentic systems
60d ago
Ground truth is a process, not a dataset
65d ago
How flat is replacing fat in AWS data center networks
72d ago
Amazon Research Awards recipients announced
72d ago
Diverse reasoning traces teach LLMs to make better decisions
73d ago
Making LLMs faster without sacrificing accuracy
84d ago
Promptimus: Improving already good LLM prompts with zero manual engineering
85d ago
Navigating uncertainty in Amazon's middle-mile network
93d ago
How mechanism design theory helps optimize Amazon-vendor collaboration
94d ago
20 loaded
MN
MIT News - Artificial intelligence
3d ago · 20 items
Solving the solvent problem
3d ago
MIT researchers are exploring sodium metal batteries as a cheaper, more abundant alternative for fast, scalable energy storage. The main challenge is sodium metal’s high reactivity, but the researchers show how choosing the right electrolyt...
The benefits of medical AI assistance vary based on user expertise
4d ago
New research found non-experts deferred to AI-based assistance in diagnosing skin cancer, even when it was wrong, while clinicians were more likely to catch AI errors.
Alexander Rakhlin named director of the MIT Statistics and Data Science Center
4d ago
Alexander ‘Sasha’ Rakhlin, the Distinguished Professor in Data, Systems, and Society, IDSS and Brain and Cognitive Sciences at MIT, has been named the next director of the MIT Statistics and Data Science Center.
Daniela Rus receives Bavarian Minister-President's High-Tech Prize
8d ago
MIT Professor and CSAIL Director Daniela Rus has received the 2026 High-Tech Prize of the Bavarian Minister-President for projects like self-organizing robot collectives, soft robotics, autonomous mobility, and brain-inspired artificial int...
Connecting research to policy on Capitol Hill
8d ago
MIT students and postdocs traveled to Washington to meet with U.S. Senate and House of Representatives staffers. Over two days, they met with over 60 offices from 32 states, advocating for policies ranging from NSF funding to AI safety.
How a medical database developed at MIT evolved into a global standard of data-sharing
9d ago
The visionary PhysioNet platform launched 25 years ago, based on a system developed at MIT in the 1970s. It has become one of the most comprehensive biomedical and clinical data repositories in existence.
Working to automate nuclear plant operations
15d ago
For nuclear to be considered as a viable clean energy source, it has to be competitively priced and economical to produce. Lauren Fortier, formerly a Naval officer and now a doctoral student in MIT's Department of Nuclear Science and E...
MIT projects selected for funding under US Department of Energy’s Genesis Mission
16d ago
MIT researchers are set to contribute to the U.S. Department of Energy’s (DOE) Genesis Mission, with 15 collaborative projects among those selected for funding under Genesis Phase I, DOE has announced.
Professor Emeritus Dimitri Bertsekas, influential computer scientist and prolific author, dies at 83
16d ago
MIT Professor Emeritus Dimitri Bertsekas, an influential researcher in many AI-related fields, a prolific textbook author, and a talented travel photographer, has died at age 83.
Following the questions where they lead
21d ago
A profile of MIT Assistant Professor Bailey Flanigan explores how she develops complex computational methods for helping democracy thrive.
A better way to turn 2D designs into 3D models for rapid prototyping
23d ago
3 Questions: Neural transparency and the future of AI design
23d ago
Helping AI models to meet the real world
24d ago
Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering
24d ago
How MIT students are helping to prevent cyberattacks
25d ago
AI agents create virtual playgrounds to help robots get crucial training data
25d ago
New method aims to keep kids safe from illegal AI-generated content
26d ago
Tiny robot boats build floating structures
29d ago
How novice coders can develop AI programs for military applications
31d ago
Jesse Thaler named director of the Laboratory for Nuclear Science
31d ago
20 loaded
MN
MIT News - Machine learning
4d ago · 20 items
The benefits of medical AI assistance vary based on user expertise
4d ago
New research found non-experts deferred to AI-based assistance in diagnosing skin cancer, even when it was wrong, while clinicians were more likely to catch AI errors.
Alexander Rakhlin named director of the MIT Statistics and Data Science Center
4d ago
Alexander ‘Sasha’ Rakhlin, the Distinguished Professor in Data, Systems, and Society, IDSS and Brain and Cognitive Sciences at MIT, has been named the next director of the MIT Statistics and Data Science Center.
A better way to turn 2D designs into 3D models for rapid prototyping
23d ago
“GIFT” is a new system that teaches vision-language generative AI models to produce accurate, computer-aided design (CAD) programs that can be used to simulate and test 3D objects. The method is more accurate than competing techniques, usin...
3 Questions: Neural transparency and the future of AI design
23d ago
MIT Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.
Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering
24d ago
MIT's JARVIS Challenge (Jet-engine AI Research and Validation Intensive Sprint) is a new academic competition asking MIT students to explore whether AI can compress the design-build-test cycle so engineers can build faster and better.
AI agents create virtual playgrounds to help robots get crucial training data
25d ago
The “SceneSmith” system developed by MIT CSAIL researchers uses AI agents to generate lifelike scenes of indoor environments like kitchens and hotels to help robots simulate everyday chores. These 3D worlds are more realistic and diverse th...
New method aims to keep kids safe from illegal AI-generated content
26d ago
Researchers developed an evaluation procedure that tests generative AI models for harmful capabilities without generating outputs. This could enable auditors to identify open-source models that have been adapted to produce illegal content, ...
Tiny robot boats build floating structures
29d ago
FloatForm, developed at MIT, is a swarm of small aquatic robots that assemble into reconfigurable structures. It could lead to floating infrastructure that builds itself into things like a temporary platform, a market, or a stage.
MIT-designed educational factory embraces modern manufacturing
30d ago
The FrED factory, a low-cost desktop fiber extrusion device designed and assembled by students in an educational factory at MIT, is changing how manufacturing is taught in Mexico through a collaboration with Tecnológico de Monterrey.
Q&A: What is agentic AI today, and what do we want it to be?
38d ago
MIT Associate Professor Phillip Isola explains what agentic AI is, how these systems are used, what applications they are best suited for, and what the future may hold for this exploding technology.
Inaugural Music Technology Research Showcase celebrates work of new graduate program’s initial students
39d ago
3 Questions: Beyond data-driven aesthetics
39d ago
LLMs help robots understand vague instructions and focus on key details
42d ago
Improving the speed and energy-efficiency of AI agents
44d ago
New chip could help tiny robots traverse complex environments
46d ago
A better way to model the behavior of metal alloys
49d ago
In game theory, generalists sometimes win out over specialists
51d ago
Could AI tell you where you left your keys?
52d ago
When it comes to predicting people’s preferences, it pays to consider “the power of three”
57d ago
Startup helps retailers track their products in real-time
64d ago
20 loaded
MR
Microsoft Research
4d ago · 10 items
Orchard: An open framework for scalable agentic AI
4d ago
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infras...
Echoverse: Deep, evolving environments for computer-use agents
8d ago
Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and env...
EvoLib: Turning experience into evolving knowledge
8d ago
LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment.
Verifying Rust cryptography in SymCrypt, from standards to code
25d ago
Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves:
Aurora 1.5: Extending open foundation models for weather and Earth-system applications
29d ago
Aurora 1.5 adds 22 more variables, hourly temporal resolution, and probabilistic ensemble forecasting to the Aurora foundation model, making it more useful for real-world weather, climate, and energy applications.
Flint: A visualization language for the AI era
30d ago
Short chart specifications are easy to write, but often produce uninspiring results. Flint is an open-source visualization language that offers a middle path, letting AI agents create expressive charts from compact, human-editable specifica...
SkillOpt: Agent skills as trainable parameters
38d ago
AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model w...
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
39d ago
AI agents can't remember past conversations. They must constantly reload or retrieve context, which grows less efficient as tasks get longer and more complex. Memora solves this with a scalable memory system separating what’s stored from ho...
Understanding the brain with AI-driven explanations and experiments
43d ago
Researchers introduce generative causal testing, which translates black box models into clear hypotheses and verifies them in the scanner, revealing what specific brain regions respond to in language.
Talos: Scaling rare disease diagnosis with automated, iterative genomic reanalysis
44d ago
Talos was built to help resolve a major bottleneck in genomic medicine: human review time. The open-source system recovered 90% of in-scope diagnoses while surfacing just 1.3 candidate variants per patient for expert review.
TL
The latest research from Google
8d ago · 20 items
Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence
8d ago
SymptomAI: Towards a conversational AI agent for everyday symptom assessment
16d ago
Towards a quantum computer that learns from its errors
16d ago
Towards demystifying the creativity of diffusion models
23d ago
SensorFM: Towards a general intelligence and interface for wearable health data
30d ago
The power of collaboration: How we can reduce traffic congestion
31d ago
Expanding our Heat Resilience data to 50+ global cities
38d ago
Introducing TabFM: A zero-shot foundation model for tabular data
39d ago
Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction
42d ago
Optimizing cloud economics with linear elastic caching
44d ago
Thinking to recall: How reasoning unlocks parametric knowledge in LLMs
44d ago
From pixels to planning: Earth AI for nature restoration
52d ago
Research into how AI can help users understand skin conditions
56d ago
A low-carbon computing platform from your retired phones
56d ago
New framework for auditing machine unlearning
58d ago
Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG
64d ago
Towards passive heart health monitoring via smartphone camera
64d ago
The next chapter in flood resilience: Open sourcing Google’s hydrology framework
65d ago
A New Era of Discovery: Google Research at I/O 2026
71d ago
Private analytics via zero-trust aggregation
72d ago
20 loaded
TB
The Berkeley Artificial Intelligence Research Blog
10d ago · 10 items
From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon
10d ago
The BAIR Blog
Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction
13d ago
The BAIR Blog
Intelligence is Free, Now What? <br> Data Systems for, of, and by Agents
32d ago
The BAIR Blog
2026 BAIR Graduate Showcase
38d ago
The BAIR Blog
Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling
92d ago
The BAIR Blog
Gradient-based Planning for World Models at Longer Horizons
110d ago
The BAIR Blog
Identifying Interactions at Scale for LLMs
148d ago
The BAIR Blog
Information-Driven Design of Imaging Systems
210d ago
The BAIR Blog
RL without TD learning
280d ago
The BAIR Blog
What exactly does word2vec learn?
341d ago
The BAIR Blog
NR
NVIDIA Research Archives | NVIDIA Blog
32d ago · 18 items
How Open Models Are Driving AI Research
32d ago
NVIDIA open models from Nemotron, Cosmos and BioNeMo are fueling the field's biggest research questions at ICML 2026.
NVIDIA Research Unlocks Advanced Grasping, Smarter Autonomous Driving and Agent Training at Scale
65d ago
New NVIDIA Research breakthroughs show how training at scale — across gripper types, driving scenarios and virtual worlds — creates AI that generalizes to diverse applications.
NVIDIA Enables the Next Era Of Physical AI Research With Agent Skills For Autonomous Vehicles, Robotics And Vision AI
65d ago
New physical AI agent skills, powered by NVIDIA Cosmos 3, help researchers accelerate data generation, simulation, policy training and evaluation for autonomous system development.
NVIDIA Research Advances Robotics From Simulation to the Real World
71d ago
Featured at the International Conference on Robotics and Automation, eight new NVIDIA Research papers show how robots trained in simulation are moving into the real world.
NVIDIA Launches Earth-2 Family of Open Models — the World’s First Fully Open, Accelerated Set of Models and Tools for AI Weather
193d ago
NVIDIA Earth-2 makes weather AI accessible worldwide at every stage — from processing initial observation data to generating 15-day global forecasts or local storm forecasts.
At NeurIPS, NVIDIA Advances Open Model Development for Digital and Physical AI
249d ago
NVIDIA releases new AI tools for speech, safety and autonomous driving — including NVIDIA DRIVE Alpamayo-R1, the world’s first open industry-scale reasoning vision language action model for mobility — and a new independent benchmark recogni...
How Do You Teach an AI Model to Reason? With Humans
345d ago
NVIDIA’s data factory team creates the foundation for AI models like Cosmos Reason, which today topped the physical reasoning leaderboard on Hugging Face.
NVIDIA Research Shapes Physical AI
361d ago
AI and graphics research breakthroughs in neural rendering, 3D generation and world simulation power robotics, autonomous vehicles and content creation.
NVIDIA Research Showcases the Future of Robotics at RSS
413d ago
At this year’s Robotics: Science and Systems conference, NVIDIA Research is presenting work that advances robot learning across simulation, real-world transfer and decision-making.
NVIDIA Scores Consecutive Win for End-to-End Autonomous Driving Grand Challenge at CVPR
423d ago
NVIDIA was today named an Autonomous Grand Challenge winner at the Computer Vision and Pattern Recognition (CVPR) conference, held this week in Nashville, Tennessee. The announcement was made at the Embodied Intelligence for Autonomous Syst...
NVIDIA Research Casts New Light on Scenes With AI-Powered Rendering for Physical AI Development
423d ago
NVIDIA Research at ICLR — Pioneering the Next Wave of Multimodal Generative AI
470d ago
Innovation to Impact: How NVIDIA Research Fuels Transformative Work in AI, Graphics and Beyond
506d ago
NVIDIA Earth-2 Features First Gen AI to Power Weather Super-Resolution for Continental US
529d ago
NVIDIA Makes Cosmos World Foundation Models Openly Available to Physical AI Developer Community
578d ago
Research Galore From 2024: Recapping AI Advancements in 3D Simulation, Climate Science and Audio Engineering
585d ago
AI’s in Style: Ulta Beauty Helps Shoppers Virtually Try New Hairstyles
596d ago
Crowning Achievement: NVIDIA Research Model Enables Fast, Efficient Dynamic Scene Reconstruction
606d ago
18 loaded
ML
Machine Learning Blog | ML@CMU | Carnegie Mellon University
49d ago · 1 items
FO
Future of Life Institute
49d ago · 20 items
Should AIs be people too?
49d ago
Statement: Anthropic warns of AI self-improvement risks, considers a pause
61d ago
FLI President on the White House Executive Order
66d ago
Magnificent Humanity – The Pope’s First Encyclical Concerns AI
79d ago
White House working group on AI – Statement from FLI’s Anthony Aguirre
94d ago
FLI’s President and CEO on Trump’s support for an AI ‘kill switch’
113d ago
FLI CEO’s statement on the attack against Sam Altman’s home
119d ago
Prominent Scientists, Faith Leaders, Policymakers and Artists Call for a Prohibition on Superintelligence, as Poll Shows Americans Don’t Want It
133d ago
Statement: Head of US Policy on the White House AI legislative recommendations
138d ago
Governor DeSantis Directs Florida State Agencies to Partner with Future of Life Institute to Shield Families from AI Harm
151d ago
“This is What it Means to be Pro-Human” Declares Broad Coalition of Conservative, Progressive, and Civil Society Groups in Statement of Shared Principles on AI
156d ago
Statement from Max Tegmark on the Department of War’s ultimatum
162d ago
Future of Life Institute Launches Multimillion Dollar Nationwide AI Regulation Campaign
179d ago
AI Company Safety Practices Fall Short of Public Commitments and Show Structural Weaknesses, as Top Performers Widen the Gap
248d ago
The U.S. Public Wants Regulation (or Prohibition) of Expert‑Level and Superhuman AI
292d ago
Michael Kleinman reacts to breakthrough AI safety legislation
308d ago
Google DeepMind Falls Behind OpenAI in Latest Safety Review; All AI Companies Still Falling Short, Say Experts
386d ago
Are we close to an intelligence explosion?
504d ago
The Impact of AI in Education: Navigating the Imminent Future
540d ago
Context and Agenda for the 2025 AI Action Summit
553d ago
20 loaded
IN
inFERENCe
163d ago · 15 items
The Future of Software
163d ago
The world of software is undergoing a shift not seen since the advent of compilers in the 1970s. Compilers were the original vibe coding: they automatically generate complex machine code that human programmers had to manually write before. ...
Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On
188d ago
Ten years ago this week, I wrote a post called "Deep Learning is Easy - Learn Something Harder". The post blew up, top spot on HackerNews. Needless to say, it didn't age well.
Discrete Diffusion: Continuous-Time Markov Chains
443d ago
A tutorial explaining some intuitions behind continuous time Markov chains for machine learners interested in discrete diffusion models.
We may finally crack Maths. But should we?
1156d ago
Automating mathematical theorem proving has been a long standing goal of artificial intelligence and indeed computer science. It's one of the areas I became very interested in recently. This is because I feel we may have the ingredients nee...
Mortal Komputation: On Hinton's argument for superhuman AI.
1165d ago
Last week in Cambridge was Hinton bonanza. He visited the university town where he was once an undergraduate in experimental psychology, and gave a series of back-to-back talks, Q&A sessions, interviews, dinners, etc. He was stopped on the ...
Autoregressive Models, OOD Prompts and the Interpolation Regime
1227d ago
A few years ago I was very much into maximum likelihood-based generative modeling and autoregressive models (see this, this or this). More recently, my focus shifted to characterising inductive biases of gradient-based optimization focussin...
We May be Surprised Again: Why I take LLMs seriously.
1234d ago
"Deep Learning is Easy, Learn something Harder" - I proclaimed in one of my early and provocative blog posts from 2016. While some observations were fair, that post is now evidence that I clearly underestimated the impact simple techniques ...
Implicit Bayesian Inference in Large Language Models
1618d ago
This intriguing paper kept me thinking long enough for me to I decide it's time to resurrect my blogging (I started writing this during ICLR review period, and realised it might be a good idea to wait until that's concluded) * Sang Michael ...
Eastern European Guide to Writing Reference Letters
1621d ago
Excruciating. One phrase I often use to describe what it's like to read reference letters for Eastern European applicants to PhD and Master's programs in Cambridge. Even objectively outstanding students often receive dull, short, factual, a...
Causal inference 4: Causal Diagrams, Markov Factorization, Structural Equation Models
1884d ago
This post is written with my PhD student and now guest author Patrik Reizinger [https://twitter.com/rpatrik96] and is part 4 of a series of posts on causal inference: * Part 1: Intro to causal inference and do-calculus [https://www.inferenc...
On Information Theoretic Bounds for SGD
1932d ago
Notes on the Origin of Implicit Regularization in SGD
1954d ago
An information maximization view on the $\beta$-VAE objective
1968d ago
Some Intuition on the Neural Tangent Kernel
2086d ago
Notes on Causally Correct Partial Models
2094d ago
15 loaded
TG
The Gradient
170d ago · 15 items
After Orthogonality: Virtue-Ethical Agency and AI Alignment
170d ago
AGI Is Not Multimodal
429d ago
Shape, Symmetries, and Structure: The Changing Role of Mathematics in Machine Learning Research
629d ago
What's Missing From LLM Chatbots: A Sense of Purpose
697d ago
We Need Positive Visions for AI Grounded in Wellbeing
734d ago
Financial Market Applications of LLMs
839d ago
A Brief Overview of Gender Bias in AI
851d ago
Mamba Explained
863d ago
Car-GPT: Could LLMs finally make self-driving cars happen?
882d ago
Do text embeddings perfectly encode text?
885d ago
Why Doesn’t My Model Work?
895d ago
Deep learning for single-cell sequencing: a microscope to see the diversity of cells
937d ago
Salmon in the Loop
965d ago
Neural algorithmic reasoning
1028d ago
The Artificiality of Alignment
1035d ago
15 loaded
VI
VITALab
214d ago · 10 items
Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge
214d ago
1. Motivation
Brain Latent Progression Individual-based spatiotemporal disease progression on 3D Brain MRIs via latent diffusion
345d ago
This article aims at reviewing a Alzheimer’s spatiotemporal disease progression predictive model called Brain Latent Progression (BrLP). All in all, this is ...
A Survey of popular LLM Evaluation Metrics
353d ago
Large Language Models (LLMs) are increasingly applied to critical domains such as medical report generation, where accuracy and trust are essential. Evaluati...
Open-Source Large Language Models in Radiology: A Review and Tutorial for Practical Research and Clinical Deployment
362d ago
Open-Source Large Language Models in Radiology
MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation
431d ago
MemSAM
Simplifying Deep Temporal Difference Learning
488d ago
tl;dr The authors propose PQN, a simplified deep online Q-Learning that uses very small replay buffers. Normalization and parallelized sampling from vectoriz...
EchoPrime: Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation
502d ago
Objective EchoPrime is a foundation model designed for comprehensive echocardiographic interpretation. Unlike previous models that use single views or static...
DeepSeek-V3 Technical Report
543d ago
DeepSeek-V3
Variational Autoencoders for Generating Synthetic Tractography-Based Bundle Templates in a Low-Data Setting
571d ago
Highlights
Implicit neural representations
599d ago
Implicit neural networks
No matching sources found.