I am a first-year PhD at Cornell University, focusing on Unified Models / Multimodal Learning / World Models. Before that, I Graduated from Beijing University of Technology (B.Eng in Artificial Intelligence).
I am also conducting computer vision research at Johns Hopkins University with Bloomberg Distinguished Prof. Alan Yuille. Previously at Peking University supervised by Prof. Wentao Zhang. I also worked at HKU promoting CT-free scoliosis treatment. I maintain close industry collaborations and have engineering experience with leading organizations. My research mainly focus on multimodal learning, unified model, and vision related topic like world model/ video gen. I am deeply interested in how models can better perceive & encode specific knowledge (e.g., physics, medicine) to enable reliable reasoning and generation.
Teaching
Coming soon.
Service
Peer-Review: ACL'26 CVPR'26, CVPR'26 Workshop Journey to the Awards: Generative AI for Movie-Grade Video Production, ICCV'25, NeurIPS'24, KDD'26, ICML'26
Invited Talk
NVIDIA Academic Grant Program 2025.
Silver Medal, China English Debate National Championship 2022.
China National Encouragement Scholarship 2022.
Outstanding Scholarship, BJUT 2021.
I love postmodernism and wasteland punk-style photography, and I wish to be a great photographer someday.
