AI News

SimBEV2X: A Large-Scale Dataset and Data Generation Tool for Multi-Task Vehicle-to-Everything Cooperative Perception (arxiv.org)

Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents (arxiv.org)

MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models (arxiv.org)

Lexical discovery in unknown environments orchestrated by Large Language Models (arxiv.org)

Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View (arxiv.org)

Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers (arxiv.org)

BoneAgeTW2: Automated Skeletal Maturation Assessment via the Tanner-Whitehouse 2 Method, Deep Learning, and Clinical Report Generation with Distribution Curves (arxiv.org)

DRP-FLR: Data-Driven Assessment of Demand Response Potential for Flexible Load Regulation in Smart Grids (arxiv.org)

Explainable Reinforcement Learning via Physics-Aware Policy Distillation (arxiv.org)

Label-free Industrial Fault Detection via Adversarial Inverse Reinforcement Learning: A System for Run-to-Failure Prognostics (arxiv.org)

DSTFView: Multi-View Cloud-Edge Workload Forecasting with Dual-Input Spatio-Temporal-Frequency Modeling (arxiv.org)

Training Language Models to Cooperate with Inference-Time Controllers (arxiv.org)

Epistemic Norms for AI Safety and Alignment Research (arxiv.org)

Too much evidence, too little time: From text to actionable recommendations through multi-objective evidence reasoning (arxiv.org)

MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models (arxiv.org)

When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction (arxiv.org)

ARdena: Scenario-driven control of real-time LLM agents (arxiv.org)

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models (arxiv.org)

AI-Assisted Causal Inference and Mediation Analyses of Environmental and Psychosocial Determinants of Subjective Cognitive Difficulties in the All of Us Research Program (arxiv.org)

A Vocabulary for Multi-Agent Automated Research Systems (arxiv.org)

MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities (arxiv.org)

Falsifiable Commitment Planning for Self-Correcting Web Agents (arxiv.org)

TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation (arxiv.org)

MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation (arxiv.org)

A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever (arxiv.org)

QFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction (arxiv.org)

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis (arxiv.org)

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration (arxiv.org)

Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis (arxiv.org)

Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions (arxiv.org)

Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers (arxiv.org)

From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledge Synthesis (arxiv.org)

Integrating Factual and Normative Industrial Knowledge via Constraint-Aware Graph Attention for Process Plan Recommendation (arxiv.org)

TRACE-CTI: Auditable Post-Extraction Governance of TTP Claims with Knowledge Graphs (arxiv.org)

A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection (arxiv.org)

Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors (arxiv.org)

ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation (arxiv.org)

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy (arxiv.org)

Online Policy Evaluation for MDPs with Dynamic UBSR Measures (arxiv.org)

Sampling Decisions: Exact Path-Space Correction, Prior Cancellation and Local-Boltzmann Guidance (arxiv.org)

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety (arxiv.org)

Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions (arxiv.org)

PYPM-GGD: Pitman-Yor Process Mixture with Generalized Gaussian Density using ADAM (arxiv.org)

CausAdv: A Causal-based Framework for Detecting Adversarial Examples (arxiv.org)

Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses (arxiv.org)

StageGuard: Physiologically Constrained Sleep Staging (arxiv.org)

All in One: Generative Modeling as Mean-Field Game Design (arxiv.org)

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness (arxiv.org)

LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports (arxiv.org)

Verification-Notebook Learning for Source-Aware Multimodal Misinformation Detection (arxiv.org)