Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms Paper • 2604.23775 • Published Apr 26 • 46 • 3
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 263 • 6
Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems Paper • 2606.00090 • Published May 23 • 6 • 4
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack Paper • 2608.03207 • Published Aug 4 • 4 • 3