Published multiple papers in top-tier conferences such as NeurIPS, SIGGRAPH, CVPR, including 'Efficient Part-level 3D Object Generation via Dual Volume Packing' and 'Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics'.
Research Experience
Research Scientist at NVIDIA Research.
Education
Ph.D. in Mathematics from UCLA, advised by Prof. Chenfanfu Jiang; M.S. in Computer Science from the State University of New York at Stony Brook; B.S. in Mathematical Sciences from Tsinghua University (China).
Background
Research interests: 3D generation and reconstruction, particularly utilizing physics-based simulation. On one hand, simulation serves as a tool to introduce dynamics into 3D scenes reconstructed from real-world data; on the other hand, exploring the integration of physics as a regularization within generation and reconstruction pipelines.