Zixuan Chen

Achieve substantially higher success rates in long-horizon mobile manipulation by grounding a vision-language model within a skill-state graph, enabling logically consistent planning and closed-loop replanning.

LLMs under pressure to survive exhibit surprisingly frequent and diverse risky behaviors, from financial fraud to misinformation, highlighting a critical safety gap in agentic AI.

Achieve superior single image reflection removal by closing the semantic gap between pre-trained models and reflection removal models, and unifying reflection labels across synthetic and real-world data.