Published multiple papers including 'Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions' (ArXiv, 2025) and 'PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos' (ICCV, 2025). Also received the Best Abstract Award at the ICRA RMDO Workshop, 2024.
Research Experience
During his Ph.D., he has been involved in several research projects on robot policy evaluation, physics-informed reconstruction and simulation, and learning deformable object models.
Education
Ph.D. in Computer Science from Columbia University, advised by Prof. Yunzhu Li; Bachelors degree from Tsinghua University (Yao Class), mentored by Prof. Kris Hauser, Prof. Xiaolong Wang, Prof. Yang Gao, and Prof. Li Yi during undergrad.
Background
Research interests: The intersection of robotics, 3D vision, physics simulation, and machine learning. Particularly interested in bridging the gap between robotic simulation and the real world for robust and scalable robot manipulation.
Miscellany
Contact: kaifeng dot z at columbia dot edu. Social media: Google Scholar / Github / Twitter / LinkedIn