Summary
Hengshuang Zhao is an Assistant Professor at The University of Hong Kong with a decade of experience researching computer vision, machine learning, and AI, focusing on intelligent visual systems that perceive, reconstruct, and generate multimodal content. He completed a PhD at The Chinese University of Hong Kong and held postdoctoral positions at MIT CSAIL and the University of Oxford, working with leading vision labs and contributing to projects spanning scene understanding, generative modeling, and embodied AI. His industry internships at Adobe, Uber, and Intel informed practical advances in image composition, panoptic segmentation for autonomous driving, and self-attention for images and point clouds. Hengshuang combines strong academic leadership with hands-on systems expertise, aiming to build AI that can imagine and interact with real-world environments. A lesser-known thread in his career is early work on precise 3D measurement and real-time shape systems showcased during a Microsoft Young Fellow program, reflecting a longstanding interest in bridging perception research and real-world sensing.
10 years of coding experience