AI News

Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability (arxiv.org)

Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts (arxiv.org)

Training-Aware Target Coverage for Synthetic Data Selection (arxiv.org)

Quantifying the Impact of Ambulance Ramping: A Multi-Year Analysis of Victorian Emergency Medical Services Cases (arxiv.org)

AnyJev Technical Report (arxiv.org)

Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series (arxiv.org)

TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models (arxiv.org)

SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning (arxiv.org)

Fixing a Model That Learned Worse Cancer Means Lower Risk: Monotonic Constraints in Bladder Cancer Recurrence Prediction (arxiv.org)

Learning to Cover Locally: Graph Neural Combinatorial Optimization under a Hard Information Horizon (arxiv.org)

How Divergence Becomes Decision Flips in Compressed Language Models (arxiv.org)

Progressive-Resolution Secure Aggregation for Federated Learning (arxiv.org)

R-GroundBench: A Diagnostic Benchmark for R-Group Groundingin Markush Molecular Editing (arxiv.org)

AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models (arxiv.org)

Reason in Style: Discovering and Controlling Style in Language Models (arxiv.org)

CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization (arxiv.org)

Q-MINO: A Minimal-Norm Method for Quantization-Aware Training (arxiv.org)

Crossing the Cyber Divide: Sim-to-Sim and Sim-to-Real Transfer for RL Agents (arxiv.org)

Inference for stochastic differential equations driven by weighted sub-fractional Brownian motion using neural networks and the Euler approximation (arxiv.org)

TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models (arxiv.org)

Video Generation Models: A Survey of Post-Training and Alignment (arxiv.org)

PI-AMFM: Permutation-Invariant Learning for Variable-Cardinality AM-FM Mode Decomposition in Biomedical Signal Analysis (arxiv.org)

VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence (arxiv.org)

Neural Fourier Surrogates for Data Reuploading Quantum Neural Networks (arxiv.org)

SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing (arxiv.org)

ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization (arxiv.org)

STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling (arxiv.org)

Block Optimism for Nonstationary Bandits with Latent Linear Dynamics (arxiv.org)

EyeTAG: Eye Trajectory-Aware Gaze Estimation (arxiv.org)

CompMat-Bench: Benchmarking AI Agents for Computational Materials Science (arxiv.org)

A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform (arxiv.org)

RPTune: Learned Context Curation for LLM Catalog Search (arxiv.org)

The Price of Correlated Tests: How Strict Should a Model Release Gate Be? (arxiv.org)

Distilling Directional Verification (arxiv.org)

Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening (arxiv.org)

Polylogarithmic Sparsity of Randomly Reweighted NPMLEs for Gaussian Mixtures (arxiv.org)

Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model (arxiv.org)

Initial condition recovery in nonlinear damped viscous photoacoustic tomography using a convolutional neural network-guided gradient-free optimization framework (arxiv.org)

Convergence Analysis of STORM Under Different Geometries (arxiv.org)

Posterior sampling by source-space MCMC via prior-based few-step transport maps (arxiv.org)

Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study (arxiv.org)

Capturing In-Context Learning Dynamics with Task Operators (arxiv.org)

MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending (arxiv.org)

Stochastic Optimal Control for Continuous-Time fMRI Representation Learning (arxiv.org)

Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting (arxiv.org)

Open Vocabulary Word Recognition From Transcribed Bangla Texts (arxiv.org)

Classical Hardness of Learning Functions of Hamiltonians (arxiv.org)

Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models (arxiv.org)

PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots (arxiv.org)

Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations (arxiv.org)