Published multiple papers in top conferences such as ICLR, NeurIPS, CVPR, including Spotlight papers like SlowFast-VGen (ICLR 2025) and 3DLLM-Mem (NeurIPS 2025 & CVPR 2025), and best paper award-winning work like 3DLLM-Mem.
Research Experience
Currently a postdoc at Stanford, advised by Prof. Yejin Choi. Previously, was also supervised by Prof. Song-Chun Zhu during early PhD years at UCLA.
Education
Ph.D. in Computer Science from UCLA, co-advised by Prof. Ying Nian Wu and Prof. Kai-Wei Chang; B.S. in Electrical Engineering from Shanghai Jiao Tong University, advised by Prof. Xinbing Wang and Prof. Weinan Zhang.
Background
Postdoc at Stanford, dedicated to building general-purpose embodied agents that could actively explore and interact with the 3D physical world, and perform common sense reasoning within the embodied environment. Specifically focuses on building 3D world model, large embodied foundation models, and visual common sense reasoning.