Assistant Professor, National University of Singapore

Research Area: computer vision, video intelligence, multimodal, embodied AI

Award Citation: The AYSF Committee acknowledges Dr. Mike Zheng Shou's pioneering contributions to multimodal video intelligence, including video-language pretraining, efficient diffusion-based video generation, and unified multimodal understanding and generation. AYSF would like to support his continued research on long-form video modeling, Video-Language-Action agents, and video world models for digital and physical environments.

Bio: Mike Zheng Shou is an Assistant Professor under the Presidential Young Professorship at the National University of Singapore. He received his Ph.D. from Columbia University and subsequently worked as a Research Scientist at Facebook AI. His research focuses on computer vision, particularly video understanding, multimodal learning, and embodied AI. He has made pioneering contributions to video-language pretraining, efficient diffusion-based video generation, and unified multimodal understanding and generation. His work received Best Paper Finalist recognition at CVPR 2022, Best Paper Candidate recognition at CVPR 2025, and the EgoVis Distinguished Paper Award. He has also won first place in international competitions associated with ActivityNet, EPIC-Kitchens, and Ego4D. He has created nine widely distributed software projects, each of which has received more than 1,000 stars on GitHub. His ShowUI model has been downloaded more than 280,000 times, and his online tutorial on “Video Diffusion Models” has been viewed more than 40,000 times. He regularly serves as an Area Chair for leading AI conferences and is an Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence. He is also an ST Engineering Distinguished Professor and was named to the Forbes 30 Under 30 Asia list.

Personal Web:https://sites.google.com/view/showlab