Research
Embodied intelligence, visual reasoning, and robot learning.
Princeton University
Visual reasoning
Research Intern
With Prof. Zhuang Liu and Prof. Danqi Chen
I work on general visual reasoning and vision-language models, with an emphasis on scalable training and reinforcement-learning methods.
Vero: general visual reasoning →University of Michigan
Research Intern
Advised by Prof. Dmitry Berenson
I study embodied AI and robot learning, including ways to equip vision-language-action policies with structured spatial guidance for adaptive manipulation.
Topology-informed visual prompting →Shanghai Jiao Tong University
Research Intern
Mentored by Prof. Yutong Ban
I worked on surgical robotics and long-horizon surgical phase recognition from full-length videos.
Hierarchical state space models for surgical videos →