AI News

Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding (arxiv.org)

STAR: Scene- and Task-Aware 4D Radar Preprocessing Towards End-to-End Cognitive Radar (arxiv.org)

Graded-Relevance Composed Multimodal Retrieval for E-commerce Visual Search at Scale (arxiv.org)

Memory vs. Context? Influential Factors of Factual Recall in Language Models (arxiv.org)

Recidivism Prediction, Peer Effect Estimation, and Prediction-Powered Inference with LLM Text Measures (arxiv.org)

Toward Personalized Sleep Guidance from Wearable Data Using Language Models (arxiv.org)

Quantum Model Parallelism for MRI-Based Classification of Alzheimer's Disease Stages (arxiv.org)

Artificial Neural Networks as Surrogate Models in Black Box Optimization (arxiv.org)

AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation (arxiv.org)

Dimensionality reduction for AI based hyperspectral image classification based on XAI (arxiv.org)

Initial Evaluation of Potential Bias in Coverage of Humans in Wikidata (arxiv.org)

MarsRecon: Self-Supervised and Multimodal Surface Representations for Mars (arxiv.org)

FRAMES: Failure Recovery And Monitoring of Embodied Skills for Humanoid Loco-Manipulation (arxiv.org)

Beyond the Leaderboard: Counterfactual Diagnosis of End-to-End and VLA Driving Policies Under Domain Shift (arxiv.org)

A Horizon-slicing Approach to Minimum Obstacle Displacement Planning for Robot Navigation (arxiv.org)

Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach (arxiv.org)

SEABED: SouthEast Asian Benchmark for Evaluating Audio Reasoning (arxiv.org)

Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act (arxiv.org)

Commonsense-Grounded Path Planning from Abstract Instructions (arxiv.org)

Fairly Compensated Distributed Information Retrieval and Augmentation for AI Agents (arxiv.org)

Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation (arxiv.org)

From Documented Strengths to Force Limits: Material-Informed Robotic Insertion for Construction Assembly (arxiv.org)

HIGenNTO: Scalable Humanoid Interaction Generation via Noise-Space Trajectory Optimization (arxiv.org)

Math2Visual-X: A Modular Framework for Pedagogically Aligned Lower-Primary Math Visuals Generation (arxiv.org)

Discovering Data Manifold Geometry through Geometric Properties (arxiv.org)

From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation (arxiv.org)

Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling (arxiv.org)

Analyzing Public Discourse on Urbanism: Topic Clustering, Sentiment Analysis and Retrieval-Augmented Generation using YouTube Comments (arxiv.org)

From Code to Requirements: Agentic Reverse Engineering of Business Rules at Enterprise Scale (arxiv.org)

MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning (arxiv.org)

Beyond Raw Engagement: A Counterfactual Observability Framework for Recommender Systems at Netflix (arxiv.org)

Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant (arxiv.org)

SelfOp: An Optimization Algorithm for Self-Improving Security Agents (arxiv.org)

Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation (arxiv.org)

AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation (arxiv.org)

Stable Unsupervised Continual Chunking with Sheaf SyncMap (arxiv.org)

Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment (arxiv.org)

Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval (arxiv.org)

Graph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines (arxiv.org)

Human-guided physics-constrained AI agents construct an auditable model of soil-plug evolution (arxiv.org)

OmniEcho: Spatial Audio Understanding for Embodied Agents (arxiv.org)

Signed Graph Pre-Training and Prompt Learning (arxiv.org)

Partner-Specific Affective Precision in Social Active Inference (arxiv.org)

Beyond PUE: A Local Impact Audit Framework for Data Center Environmental Accountability (arxiv.org)

RiverVLN: Phase-Grounded Temporal Vision--Language Navigation for Unmanned Surface Vehicles (arxiv.org)

PhysReflect: Geometry and Perception Guided Diffusion for Physically-Plausible Mirror Reflections (arxiv.org)

Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations (arxiv.org)

Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models (arxiv.org)

A Global Comparison of Schemas, Transparency, and Interoperability in Public-Sector AI Registers and Inventories (arxiv.org)

RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents (arxiv.org)