I am a research scientist in Vladlen Koltun‘s org at Apple, working on video world model and depth estimation. Previously, I worked at Apple SLAM team for ARKit. I earned my Ph.D. degree in Computer Science at UC Berkeley. My dissertation is on “Learning to Detect Geometric Structures from Images for 3D Parsing”. Before Berkeley, I received my Bachelor’s degree from Yao Class at Tsinghua University.

My expertise lies in video/image synthesis, depth estimation, and neural rendering, with a broader interest in emerging technologies. My PhD research focused on geometric deep learning from images.