Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms Paper • 2604.23775 • Published 6 days ago • 44
AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration Paper • 2604.01014 • Published about 1 month ago • 11
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models Paper • 2603.15557 • Published Mar 16 • 29