AI News

Linear Bandits under Exact Sliding-Window Constraints (arxiv.org)

On the Computational Tractability of Robust Bandits (arxiv.org)

Optimal and Efficient Online Inverse Optimization (arxiv.org)

GeneICL: A Tabular Foundation Model for Bulk Transcriptomics (arxiv.org)

Probabilistic Counterfactual Inference for Discrete Outcomes in Gaussian-Process Causal Models (arxiv.org)

Modeling Latent Disturbances for Robust Decision-Making in World Models (arxiv.org)

Recurrent Looped Transformer (arxiv.org)

OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception (arxiv.org)

Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation (arxiv.org)

A Systematic Study of Small Language Models on Abstract Reasoning Tasks (arxiv.org)

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? (arxiv.org)

Making COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT Evaluation (arxiv.org)

Energy-Aware Path Following: Comparative Analysis of Reinforcement Learning and NMPC for Electric Vehicles (arxiv.org)

AX is the New AEO (arxiv.org)

Calibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring (arxiv.org)

SWE-Game: Can Coding Agents Build the Games We Want? (arxiv.org)

When Does a Second Model Help? Cross-Model Review in LLM Verification (arxiv.org)

Beyond the Leaderboard: Multi-Dimensional Evaluation of Dense and Mixture-of-Experts Models for Automated Program Repair (arxiv.org)

Surviving the Router: Optimizing Skill Injections for Retrieval and Execution (arxiv.org)

Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures (arxiv.org)

Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training (arxiv.org)

KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arxiv.org)

Infrared Subtraction with Artificial Intelligence (arxiv.org)

FOSLS-deRhaNN: native de Rham neural classes for H(div) and H(curl) with applications to first-order system least-squares neural network methods for partial differential equations (arxiv.org)

Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution (arxiv.org)

Learning consistent molecular mechanics force fields from first principles (arxiv.org)

Rethinking Faithfulness in LLMs: A Pairwise Context-Sensitive Perspective (arxiv.org)

Learned Adaptive Multiresolution Diffusion Imaging (arxiv.org)

Scen-Opt: A Scenario Optimization Toolbox for Data-Driven Convex Programming (arxiv.org)

CHARTER: Auditing Reference Substitution in Hierarchical Compact-Evidence Evaluation for Computational Pathology (arxiv.org)

CrystalJev: thinking fast and slow with atomistic foundation models for materials discovery (arxiv.org)

Agentic RCA for Internet-Scale Services Using Constrained Creativity (arxiv.org)

A Swarm-Coordinated Multi-Robot System for Early Stress Detection in Agricultural Rows Using Multimodal Leaf Sensing (arxiv.org)

One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control (arxiv.org)

How High Is 0.6? Floors, Ceilings, and Headroom in Interpretability Probing (arxiv.org)

Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction (arxiv.org)

Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks (arxiv.org)

APEX: Speculate smarter, not deeper (arxiv.org)

Learning to Retrieve via Reinforcement Learning in Embedding Space (arxiv.org)

Emoception: Selective Affective Layer Fine-Tuning of Video Vision Transformers for Player Arousal Change Recognition From Gameplay Footage (arxiv.org)

SanSi: A Looped Typed Decision Model for System 1.5 Thinking (arxiv.org)

The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models (arxiv.org)

RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing (arxiv.org)

Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction (arxiv.org)

MedCORE: Criteria-Grounded Clinical Reasoning for Interpretable Medical Image Diagnosis (arxiv.org)

Wiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World Discussions (arxiv.org)

Language-model ratings of depression reflect the rater more than the patient (arxiv.org)

Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment (arxiv.org)

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability (arxiv.org)

Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models (arxiv.org)