AI News

RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning (arxiv.org)

TopoFE: topology-aware LLM-guided Automated Feature Engineering (arxiv.org)

Key-Interval A*: Accelerating Grid Pathfinding via Structural Abstraction (arxiv.org)

An Unofficial FastLAS Tutorial: A Programmer's Guide (arxiv.org)

Ordered Network Analysis of Epistemic Emotions during Collaborative Problem Solving (arxiv.org)

ML-based Predictive Models for Power Consumption in Virtualised O-RANs (arxiv.org)

Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic Clutter (arxiv.org)

Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models (arxiv.org)

MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution (arxiv.org)

Neural Representation of Minimal Surfaces (arxiv.org)

ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control (arxiv.org)

Novel Claim or D\'ej\`a Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking (arxiv.org)

Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation (arxiv.org)

Continuous surrogates versus threshold Boolean networks for modeling Arabidopsis ISR gene regulation (arxiv.org)

SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents (arxiv.org)

PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation (arxiv.org)

LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings (arxiv.org)

TRE: Training-Free Hallucination Detection for Diffusion Language Models (arxiv.org)

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion (arxiv.org)

Stochastic Counterdiabatic Driving via Biorthogonal Liouvillian Eigenmodes (arxiv.org)

Learned Interventions in Lean 4 grind (arxiv.org)

SymStep: Symbolic Step Verification for Logical Reasoning (arxiv.org)

Rendering on Real Silicon: GPU Render-Timing as a Passive, AI-Resistant CAPTCHA Signal (arxiv.org)

Self-Attention Dynamics with Rotary Position Embeddings: Twisted States and Explicit Consensus Rates on the Sphere (arxiv.org)

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations (arxiv.org)

Extending Desbordante with Probabilistic Functional Dependency Discovery Support (arxiv.org)

CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding (arxiv.org)

Variational-Ising-Attention (VIA):TailoredAttentionMattersfor Science (arxiv.org)

DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes (arxiv.org)

What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation (arxiv.org)

DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory (arxiv.org)

Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review (arxiv.org)

Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models (arxiv.org)

K-Survival Means (arxiv.org)

Every Client Is an Environment: Federated De-confounding for Spatio-Temporal Forecasting (arxiv.org)

EgoPlay: Event-Triggered Video Editing for Egocentric Streams (arxiv.org)

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift (arxiv.org)

Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models (arxiv.org)

A Few Words Go a Long Way: Language Guided Robot Policy Synthesis (arxiv.org)

Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning (arxiv.org)

D-Score: A Spectral Hidden-State Signal for Hallucination Detection in Large Language Models (arxiv.org)

ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (arxiv.org)

MMOE: Modernizing Diffusion Transformers with Efficient Expert Design (arxiv.org)

Share No More Than the Request Requires: Federated Disclosure for Perspective-Aware AI (arxiv.org)

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems (arxiv.org)

Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registration (arxiv.org)

Maximum Satisfiability of Simple Temporal Problems (arxiv.org)

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications (arxiv.org)

Optimizing Transformer Neural Network for Real-Time Outlier Detection on FPGAs (arxiv.org)

PathScale-R1: Cross-scale Reasoning for Pathological Image Analysis (arxiv.org)