
Flow Matching Reinforcement for 3D Mesh Generation via Dynamic Homing Optimization
arXiv arXiv preprint, 2026
Researcher · Tencent Hunyuan · Shenzhen, China
I am currently a Researcher at Tencent Hunyuan, working on 3D computer vision and graphics.
Prior to this, I obtained my Ph.D. degree from Tsinghua University, where I was fortunate to be supervised by Prof. Ruqi Huang. I received my M.S. degree in Computer Vision from the University of Michigan. During COVID-19, I worked as a research assistant at Tsinghua University under Prof. Lu Fang. I received my B.S. degree from Huazhong University of Science and Technology in 2019.
Neural rendering (NeRF, 3D Gaussian splatting), multi-view reconstruction and 3D asset generation.
Automatic rigging, skinning, and motion generation for articulated characters.
Non-rigid shape matching, functional maps and point cloud registration.
Selected work on 3D vision, graphics and geometric learning.

arXiv arXiv preprint, 2026



SIGGRAPH ACM SIGGRAPH (SIGGRAPH), 2026

3DV International Conference on 3D Vision (3DV), 2026

NeurIPS Conference on Neural Information Processing Systems (NeurIPS), 2025

arXiv arXiv preprint, 2025

arXiv arXiv preprint, 2025

arXiv arXiv preprint, 2025

CVPR Conference on Computer Vision and Pattern Recognition (CVPR), 2025

CVPR Conference on Computer Vision and Pattern Recognition (CVPR), 2025

SIGGRAPH Asia SIGGRAPH Asia, 2024

NeurIPS Conference on Neural Information Processing Systems (NeurIPS), 2023

ICCV International Conference on Computer Vision (ICCV), 2023

CVPR Conference on Computer Vision and Pattern Recognition (CVPR), 2023

ENGINEERING ENGINEERING, 2023