AI News

Probing the limits of forward screening and inverse design of crystal materials (arxiv.org)

Whispering Wisely: Smart Subset Selection for ASR Fine-Tuning (arxiv.org)

GEMS-RAG: Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation (arxiv.org)

Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models (arxiv.org)

CFL-aware edge design for graph neural solvers of hyperbolic transport (arxiv.org)

CodeMeepo: A Multi-Agent Workflow for Repository-Level Code Migration and Optimization (arxiv.org)

Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation (arxiv.org)

Energy Efficient Lung Tumor Segmentation with a modified CBAM ENet Skip Model (arxiv.org)

ProtoEEG: Structured Prototype Alignment for EEG Visual Decoding (arxiv.org)

Linear Probes Transfer from Base to Distilled Language Models despite Rotation (arxiv.org)

StateWise: Teaching Language Models to Track and Obey Evolving Constraints in Multi-Turn Dialogue (arxiv.org)

Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews (arxiv.org)

ArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps (arxiv.org)

One-Shot Federated Model Editing for Device Dynamics at the Edge (arxiv.org)

Announced Breaks Separate Conformal Reliability from Frequency Calibration (arxiv.org)

VLMProbe: An Open-source Library for VLM Probing and Interpretation (arxiv.org)

When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems (arxiv.org)

PhaseBreak: Proactive Temporal Protection against Unauthorized Image-to-Video Animation (arxiv.org)

AgentProofBench: Benchmarking Reusable Verifiers for Web Agents (arxiv.org)

Test-Time Confidence Adaptation under RL-Induced Trajectory Shift (arxiv.org)

E3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges (arxiv.org)

TriageRAG: Failure-Aware Self-Training for Adapting Retrieval-Augmented Language Models to Specialized Domains (arxiv.org)

Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations (arxiv.org)

WorldFailBench: Do World Models Understand Policy Failures? (arxiv.org)

PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds (arxiv.org)

Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs (arxiv.org)

Diagonally-Weighted Generalized Method of Moments Estimation for Gaussian Mixture Modeling (arxiv.org)

Context Is Not Free: Carbon-Aware LLM Routing for Multi-Turn LLM Web Services across Geo-Distributed Data Centers (arxiv.org)

When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training (arxiv.org)

Entity Matching using Decision Models (arxiv.org)

Beyond Heuristics and Commercial Navigation: An AI-Augmented Decision-Support for Ambulance Travel Time Estimation (arxiv.org)

Winner's Curse Drives False Promises in Data-Driven Decisions (arxiv.org)

Audit Where Hacks Pay: Budgeted Strong-Verifier Audits Against Reward Hacking in GRPO (arxiv.org)

Joint Latent Reasoning and Observation for Agentic Video Understanding (arxiv.org)

GeoLEON-CLIP: Graph-Anchored Multimodal Contrastive Learning for Geographic Region Representation (arxiv.org)

Can Loan Processors and Underwriters Spot AI-Edited Statements? An Empirical Study (arxiv.org)

Joint Independence Testing for Latent Position Random Graphs (arxiv.org)

Kernelised covariance matrices, dimension reduction and imbalanced spectral clustering (arxiv.org)

Online Covariance Estimation for Averaged Stochastic Gradient Descent on Riemannian Manifolds (arxiv.org)

Affine-invariant Cubic Newton with Weak Learners (arxiv.org)

On the Error Analysis of Triangular Transport Maps for Conditional Generation via MMD-based Objectives (arxiv.org)

BatMIL: Geometry-Embedding State Space Model for Whole-Slide Image Representation (arxiv.org)

Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking (arxiv.org)

GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment (arxiv.org)

Depth Improves Training-Time Scaling for Difficult Tasks in Deep Linear Networks (arxiv.org)

RoboGene: Diversity-Driven Agentic Task Generation Framework for VLA Pre-training (arxiv.org)

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation (arxiv.org)

EpiFlow: Bridging Safety and Performance in Offline Reinforcement Learning via Epigraph-Guided Flow Matching (arxiv.org)

How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study (arxiv.org)

Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks (arxiv.org)