AI News

CogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection (arxiv.org)

Clinically Interpretable Biological Age Estimation Using CatBoost and SHAP with Continuous and Categorical Features from NHANES (arxiv.org)

SHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations (arxiv.org)

Does Compression Imply Generalization? A Minimum Description Length Perspective (arxiv.org)

Memorilla: Latent Semantic Memory for LLMs (arxiv.org)

Same Target, Different Origins: Aligning Latent Rollout for Consistent PDE Emulation (arxiv.org)

Honesty is the Best Policy ... or is it? Demand Management for Probabilistic Service Options (arxiv.org)

Sci$\Pi$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents (arxiv.org)

OmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformatics (arxiv.org)

Athanor: An Agent-Native System for Autonomous Post-Training Research (arxiv.org)

Learning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language Agents (arxiv.org)

Recursive Reward Improvement via Adversarial Meta-Prompt Evolution (arxiv.org)

Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation (arxiv.org)

Long-Context Drafting Does Not Require Long-Context Drafters (arxiv.org)

Denoising Score Matching in Diffusion Models: The Effect of Rank Constraints on Generalization (arxiv.org)

Amortizing Sequential Experimental Design in Reasoning LLMs (arxiv.org)

Task-Phase-Conditioned Expert Routing Is Not a Reliable Proxy for Quantization Sensitivity in MoE FFN Tensors (arxiv.org)

O-RAN-Native Jamming Detection Under Network Heterogeneity (arxiv.org)

Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards (arxiv.org)

Optimal Explicit and Implicit Regularization Strengths in High-Dimensional Continual Linear Regression (arxiv.org)

EEG-Based Prediction of Music Enjoyment Using Deep Learning with Explainable Temporal Analysis (arxiv.org)

RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases (arxiv.org)

Evaluating Model Capabilities After Benchmark Saturation (arxiv.org)

Sliced Wasserstein Sketches with Error Certificates (arxiv.org)

Selection-Safe Conformal Early Exit: Distribution-Free Coverage under Adaptive Depth (arxiv.org)

Semantic Alignment of EEG and Text: A Contrastive Learning Framework for Decoding Imagined Speech (arxiv.org)

Optimal Hydra: Model Heterogeneous Federated Learning for LLMs using Data-Informed Hydra-Nets (arxiv.org)

Interpreting Language Model Parameters (arxiv.org)

RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention (arxiv.org)

Learning Topology-Aware Representations for Mechanics-Relevant TPMS Metamaterials (arxiv.org)

Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility (arxiv.org)

Designing Experiments for External Decision Makers (arxiv.org)

Robust Covariance Estimation for Entry-wise Contaminated and Partially Observed Data via Expectation Maximization Algorithm (arxiv.org)

Conditional Mean Flows: Few-Step Densities for Simulation-Based Inference (arxiv.org)

LCT: Losslessly Compressed Tensors with GPU friendly execution for Training (arxiv.org)

When Is Muon Optimal? Radial Fragility and Minimax Geometry (arxiv.org)

Two-Stage Score Estimation for Group-Specific Diffusion Models (arxiv.org)

Stochastic Gradient Descent: A Nonlinear Time Series Perspective (arxiv.org)

Complete or Sparse: A Tale of Two Identifiabilities (arxiv.org)

On the Stability and Convergence of Flow Map Training (arxiv.org)

In-Context Learning Before Specialisation: Theory of Learning in a Solvable Topic Model (arxiv.org)

Classical methods for modern applications: synthetic tabular data generation using lightweight discrete response continuous latent variable model (arxiv.org)

Sharp and Stable Label-Free Calibration Certificates from Logical Coherence (arxiv.org)

Two Sample Sizes in Test-Time LLM Ensembling: Buffered ERM and Minimax Theory (arxiv.org)

Controlling the False Discovery Rate via Model-Agnostic Importance Measures (arxiv.org)

A One-Sided McDiarmid-Type Inequality for Heavy Tails via Reverse KL Tensorization (arxiv.org)

StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction (arxiv.org)

On the Last-Iterate Convergence of Clipped Gradient Methods (arxiv.org)

Failure Is the Mother of Success: Recovering Supervision with Grounding Hindsight (arxiv.org)

Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet Processes (arxiv.org)