Published multiple papers, including 'LookOut: Real-World Humanoid Egocentric Navigation' at ICCV 2025, 'MultiPhys: Multi-Person Physics-aware 3D Motion Estimation' at CVPR 2024, and others.
Research Experience
Research Scientist at Luma AI, building the next-gen unified multimodal model. Worked at NVIDIA, Adobe, and Meta. Served as a research mentor for the Computer Vision team at Stanford AI4ALL.
Education
Ph.D. in Computer Science from Stanford University, advised by Professor Leo Guibas; M.S. in Electrical Engineering from Stanford University, advised by Professors Juan Carlos Niebles and Fei-Fei Li; B.S. from South China University of Technology.
Background
Research Interests: Computer Vision, particularly perceiving and simulating human-world interactions. Professional Field: Computer Science.