Fengling Li

Prompt framing is the leading factor in jailbreak vulnerabilities, revealing critical gaps in multimodal safety alignment that could have serious implications for real-world applications.

A single adversarial texture can compromise the performance of Vision-Language-Action models across multiple tasks, revealing alarming shared vulnerabilities.

Forget relying on immediate observations: Keyframe-Chaining VLA lets robots nail long-horizon tasks by remembering and chaining together only the *important* past states.