AI News

Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents (arxiv.org)

HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived Segments (arxiv.org)

The Troy Moment of AI: Why SomeWill Cheat and SomeWill Follow? (arxiv.org)

Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models (arxiv.org)

Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA (arxiv.org)

GRIN+: Towards Fast Yet Effective Machine Unlearning for Imbalanced Medical Data (arxiv.org)

Diversified and Perceptible Counterfactual Examples Leveraging Expert Knowledge (arxiv.org)

Potential of Artificial Intelligence Algorithms for Identification of Relevant Diagnostic and Prognostic Biomarkers of Early-Stage Liver Cancer (arxiv.org)

EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models (arxiv.org)

NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities (arxiv.org)

Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction (arxiv.org)

Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification (arxiv.org)

Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help (arxiv.org)

TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection (arxiv.org)

PolicyMem: Geometric Policy Memory for LLM Governance (arxiv.org)

GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory Prediction (arxiv.org)

Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration (arxiv.org)

Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language Models (arxiv.org)

CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detection (arxiv.org)

LePlanner: An Iterative Amortized Controller For World Models (arxiv.org)

ReWeight: Leveraging Human Data for VLA Post-Training via Demonstration Retrieval and Sample Weighting (arxiv.org)

Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and Interpretability (arxiv.org)

The average-farmer illusion in language-model simulations of agricultural decisions (arxiv.org)

Solving Finite-sum Coupled Compositional Optimization via Multi-block-Single-probe Estimator (arxiv.org)

A Language-Guided Multimodal Foundation Model for Zero-Shot and Multi-Task Brain Signal Analysis (arxiv.org)

Sylvas: Synergistic Learning Value based Device Scheduling in Federated Continual Learning (arxiv.org)

Transfer Learning for Socioeconomic Estimation in Forced-Displacement Settings (arxiv.org)

MoveBench: A Benchmark for Global-Scale Wildlife Movement Forecasting (arxiv.org)

Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression (arxiv.org)

Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations (arxiv.org)

Certification cost of quantum models: measurement correlation, not parameter count (arxiv.org)

NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass (arxiv.org)

Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference (arxiv.org)

Toward a Layer-2 Trigger for AI/ML Lifecycle Management in 6G (arxiv.org)

Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation (arxiv.org)

Sharing standardized image-derived data in computational pathology using DICOM (arxiv.org)

Learning Multi-Agent Task Assignment and Navigation in the Factory: from Simulation to Real Robots (arxiv.org)

AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A Comprehensive Evaluation Framework for Algorithm Analysis and Complexity Theory (arxiv.org)

Channel-Adaptive Region Adjacency Graph Carriers for Semantic Image Communication (arxiv.org)

Parameter isolation with domain-specific experts for incremental audio classification (arxiv.org)

HELENA for 5G NR LEO NTN Channel Estimation: A Comparative Evaluation (arxiv.org)

CCMAN: Cognitive Instability-Aware Cross-Modal Attention Network for Interpretable Temporal Biomarkers of Verbal Fluency Speech (arxiv.org)

A Personalized Dynamic Balance Evaluation Paradigm for Hip Exoskeleton-Assisted Walking under Unexpected Ground Perturbations (arxiv.org)

Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of Machine Translation (arxiv.org)

Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for Reliable Clinical LLM Answer Selection (arxiv.org)

TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals (arxiv.org)

Prescreening Point Defects in Semiconductors With Machine Learning (arxiv.org)

An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB (arxiv.org)

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning (arxiv.org)

Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions (arxiv.org)