EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments Paper • 2606.13681 • Published Jun 11 • 146
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction Paper • 2606.02540 • Published Jun 1 • 10
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models Paper • 2605.30161 • Published May 28 • 55
BIOCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models Paper • 2510.20095 • Published Oct 23, 2025 • 1