AI News

Chance-Constrained Belief-Space Maneuver Planning for Autonomous Collision Avoidance Under Uncertainty (arxiv.org)

Hindsight Bias in Clinical Temporal Reasoning: How Future Data Exposure Affects Large Language Model Judgment (arxiv.org)

Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G Networks (arxiv.org)

Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse Materials Design (arxiv.org)

Edge-addition monotonicity of positive p-energy fails for every p >= 1 (arxiv.org)

Generative AI and Extended Reality in Collaborative Architectural Design Education: An Exploratory Studio Study (arxiv.org)

Building a Production Greek-English Speech Recognizer (arxiv.org)

Canaries in the Bank: Auditing User-Level Privacy in Private Evolution (arxiv.org)

Positive Topology and Feasible Refinement: Forcing Matrices, Positivity, and Information (arxiv.org)

Domain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models (arxiv.org)

Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs (arxiv.org)

mKernel: Fast Multi-GPU, Multi-Node Fused Kernels (arxiv.org)

Predictive audio representations for early detection and tracking of hidden dynamic objects (arxiv.org)

FaithfulBench: Does AI Counsel Uphold or Undermine the User's Professed Faith? (arxiv.org)

LayerRoute: Adaptive Layer-Skipping with LoRA-Preserved Quality for Efficient LLM Inference (arxiv.org)

Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding (arxiv.org)

OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise (arxiv.org)

Building Legal Reward Models for Grounding and Abstention (arxiv.org)

A property-registry contract for retrieve-or-refuse thermal-mechanical lattice search (arxiv.org)

Calibrating Interpretability Instruments Before Trusting Their Verdicts (arxiv.org)

Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families (arxiv.org)

From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Image-Grounded Review Assistance (arxiv.org)

TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps (arxiv.org)

CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems (arxiv.org)

Semantic-TVM: Structure-Preserving Trustworthy Virtual Memory for Memory-Augmented and Tool-Using Agents (arxiv.org)

Overflip: Repetition-Induced Label Flips in Guardrail Models (arxiv.org)

Four Ledgers, Not One Score: Responsible Communication of LLM-Judge Calibration in Biomedical ML (arxiv.org)

Horizon-specific Expert Fusion for Photovoltaic Power Forecasting (arxiv.org)

Variational Template Matching with Statistical Fusion for Anomaly Detection in Patterned Structures (arxiv.org)

CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching (arxiv.org)

Inherited Heads: Audio language models track speakers with their text backbone's attention, and an attention-mass ranking retrieves a different set (arxiv.org)

A Machine Learning Framework for Fault Detection, Isolation, and Severity Prediction of Autonomous VTOL Aircraft (arxiv.org)

ZAPS: Zero-Cost Active Proxy Search for Neural Architecture Search (arxiv.org)

Entropy-Punctured Bloom Filters for Memory-Efficient Machine Learning (arxiv.org)

Data-free On-policy Distillation (arxiv.org)

Graph-Transformer Fraud Detection with Self-Supervised Pretraining and Conformal Risk Control (arxiv.org)

CoArena: Evaluating Computer-Use and Multi-Agent Systems in Real Time (arxiv.org)

Bayesian optimization with kernel ensembles and disagreement-based acquisition for source localization and acoustic inversion (arxiv.org)

Biquaternionic Space with Complex-valued Attention for Temporal Knowledge Graph Completion (arxiv.org)

Learning Source Acquisition Policies by Offline Planning (arxiv.org)

Communication-Efficient LLM Adaptation over Decentralized GPU Meshes (arxiv.org)

Multimodal deep learning from spectra for small-molecule structure identification: enhancing robustness with mixed-condition training (arxiv.org)

Towards Identifying the Dataset Biases Causing Phantom Transfer (arxiv.org)

Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning (arxiv.org)

Retrieval-Guided Fine-Tuning as Noisy Estimation: Risk bounds and Architectural Analysis (arxiv.org)

EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition (arxiv.org)

Should All Noises Be Treated Equally: Impact of Input Noise Variability on Neural Network Robustness (arxiv.org)

GNN4PPM: Multi-Target Predictive Process Monitoring with Relational Graph Convolutional Networks (arxiv.org)

Selecting k Paths with the Minimum Longest Path Length in the Stochastic Semi-Bandit Setting (arxiv.org)

Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design (arxiv.org)