Published multiple papers on topics including multimodal video generation, multimodal action conditioned video prediction, and joint understanding of visual and tactile signals; involved in various projects and presented research at top-tier conferences like ICCV, ICLR, and CVPR.
Research Experience
Served as a reviewer for several conferences such as CVPR, ICCV, ECCV, etc.; conducted research internships at NVIDIA and Adobe; served as a course assistant at MIT and Stanford.
Education
Ph.D. student at MIT CSAIL, advised by Prof. Antonio Torralba; worked with Prof. Leonidas Guibas and Prof. Gordon Wetzstein at Stanford; also worked with Prof. Emily Whiting and Prof. Kate Saenko.
Background
Research Interests: Multimodal learning and generative models. Specializes in generic multimodal generative models and physically-informed generative digital twins.
Miscellany
Received the Robert J. Shillman Fellowship and College Prize For Excellence in Computer Science (GPA Rank: 1st); personal interests not mentioned.