AI News

R\'enyi Tracking Bounds for Langevin Dynamics with Moving Targets (arxiv.org)

Functional BART with Shape Priors: A Bayesian Tree Approach to Constrained Functional Regression (arxiv.org)

Breaking the $T^{2/3}$ Barrier for Sequential Calibration (arxiv.org)

Bayesian Quadrature (arxiv.org)

F-DACE: Fuzzy Disagreement-Aware Causal Evidence Fusion for Abstention-Safe Conversational Retail Decision Support (arxiv.org)

Information Set Emulation: Causal Certificates for AI Derived EHR Features (arxiv.org)

Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction (arxiv.org)

The Free Inference Dimension: Complexity Measure for Zero-Collision Navigation under Hypothesis Mixtures (arxiv.org)

Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks (arxiv.org)

Learning Multi-Humanoid Pickup and Transport via Decentralized Object-Centric Control (arxiv.org)

When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments (arxiv.org)

MoRE: Mixture of Reused Experts (arxiv.org)

Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents (arxiv.org)

HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models (arxiv.org)

Evolutionary Ensemble Search: Council-Guided Program Evolution with Persistent Memory (arxiv.org)

Independence-System Realisations in Single-Source Unsplittable Flow (arxiv.org)

Prior-Free Competitive Ratios for Improving Bandits: Scale, Curvature and Horizon Are Free, but Not Jointly Under Noise (arxiv.org)

GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models (arxiv.org)

QiT: Quantum-Inspired Transformer for Visual Recognition Task (arxiv.org)

The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models (arxiv.org)

Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments (arxiv.org)

Flag Game: A Toy Model for Mechanistic Swarm Interpretability (arxiv.org)

Lecture notes on Physics Informed Neural Networks, Neural Operators, and their applications (arxiv.org)

iMINDBench: iEEG Multi-Institution Neural Decoding Benchmark (arxiv.org)

MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education (arxiv.org)

Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization (arxiv.org)

Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry Reasoning (arxiv.org)

Function Lives Where Variance Doesn't: Task-Weighted Charts of a Language Model's Computation (arxiv.org)

Suppressed, Not Erased: A Representational Trace of Edited Facts Survives Even Weight-Free Knowledge Editing (arxiv.org)

Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data (arxiv.org)

Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows (arxiv.org)

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents (arxiv.org)

Version- and Scope-Aware Question Answering over Normative Documents: A Deployed System and an End-to-End Evaluation at Production Scale (arxiv.org)

FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection (arxiv.org)

Clueing up LLMs with Tool-Augmented Deductive Reasoning (arxiv.org)

Which LLM is Best for Translating Natural Language Goals to PDDL (arxiv.org)

Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning (arxiv.org)

The Uneven Impact of Generative AI on Student Learning: Examining the Roles of Reliance, Evaluation Literacy, and Course Policy in AI-related Courses (arxiv.org)

Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection (arxiv.org)

Learning Fractional-Order Dynamics from a Single Trajectory (arxiv.org)

Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making (arxiv.org)

TRIPROBE: Probing Task Separability Beyond Classification for XAI (arxiv.org)

AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution (arxiv.org)

Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models (arxiv.org)

Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing (arxiv.org)

Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery (arxiv.org)

The Mirage of Calibrated Confidence: Trajectory-Independence of Verbalized Confidence in Vision-Language Models (arxiv.org)

Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated Driving (arxiv.org)

Limits of Transfer Learning (arxiv.org)

WetRobo: A Reproducible Robot Kit for Coding Agents in Biological Laboratories (arxiv.org)