Jian Zhu

The paper introduces EvoJail, an automated multi-objective evolutionary framework that systematically discovers diverse and effective long-tail jailbreak attacks against LLMs by optimizing for attack effectiveness and minimizing output perplexity.

DeMaVLA is a generalizable Vision-Language-Action foundation model designed for deformable object manipulation, achieving strong real-world performance on folding tasks by leveraging large-scale real-world data and corrective learning.