AI News

Verifiable Social Reasoning for LLM Assistants (arxiv.org)

Grounding SWE-Agent Decisions in Architecture-0 Design: Navigating Unknown Unknowns through Physical Mapping (arxiv.org)

FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence (arxiv.org)

Multimodal Cultural Heritage Architectural Style Classification for Residential Buildings in the UAE Based on CLIP Embeddings and SVM (arxiv.org)

MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis (arxiv.org)

Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation (arxiv.org)

Beyond "ChatGPT Can Make Mistakes": Designing Interventions to Support Metacognitive Monitoring in AI-Assisted Work (arxiv.org)

Diagnosing the Fact-Grounding Gap in Multi-Hop Question Answering (arxiv.org)

Distributed JEPA: A Self-Supervised Framework for Energy Forecasting (arxiv.org)

The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment (arxiv.org)

AeroLat: Channel-Aware Latent Space Semantic Communication for Decentralized UAV Swarms (arxiv.org)

Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation (arxiv.org)

Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling (arxiv.org)

Verbalizing Subliminal Learning Effects Using Text Optimization (arxiv.org)

VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal (arxiv.org)

The Evolution of Coordination in a Collective Intelligence System: 25 Years of English Wikipedia and the Emergence of Generative AI (arxiv.org)

RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models (arxiv.org)

StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token Selection (arxiv.org)

What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking (arxiv.org)

AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale (arxiv.org)

RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue (arxiv.org)

Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal repertoires using frozen audio encoders (arxiv.org)

Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems (arxiv.org)

A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data (arxiv.org)

ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation (arxiv.org)

Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models (arxiv.org)

Vision And Text Transformer For Predicting Answerability On Visual Question Answering (arxiv.org)

The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphs (arxiv.org)

A Cyber Range Evaluation of Autonomous Network Incident Response Agents (arxiv.org)

State of Thought Enables Endogenous Reasoning (arxiv.org)

Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents (arxiv.org)

UDAV: Uncertainty-Driven Adaptive VLM Waypoint Planner (arxiv.org)

How Humans and LLMs Read Gender into Gender-Neutral Physical Descriptions (arxiv.org)

Auto-HSI: Personalized human control of a robot swarm on demand by using LLMs for online automatic code generation (arxiv.org)

From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study (arxiv.org)

SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing (arxiv.org)

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents (arxiv.org)

3D Field Data Reduction with Adaptive Sample-Based Gaussian-Encoded Reconstruction (arxiv.org)

Are We Grading Properly? Understanding Failure Modes in Medical Benchmarks (arxiv.org)

ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication (arxiv.org)

EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation (arxiv.org)

Measuring AI harms with multidimensional Lorenz Zonoids (arxiv.org)

Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety (arxiv.org)

Few-Shot Degradation Is Not What It Seems: Behavioral Evidence, Representation Analysis, and a Random-Text Control Across 12 Models, 2 Tasks, and 2 Architectures (arxiv.org)

Nonsmooth Optimization via Orthogonalized Momentum (arxiv.org)

ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation (arxiv.org)

FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection (arxiv.org)

William Buckland's Theology of Geology (www.historytoday.com)

RepoRoad (www.producthunt.com)

Die With Me (www.producthunt.com)