Yusu Fang

Undergrad @ EECS, PKU.

me.png

I am a senior undergraduate student from School of EECS, Peking University.

Currently, I am fortunately to be advised by Prof. Ehsan Adeli at Stanford Vision and Learning (SVL) Lab, Prof. Lingjie Liu and Prof. Kostas Daniilidis at UPenn GRASP Lab. I also work closely with Prof. Fei-Fei Li and Prof. Scott Delp.

In general, my research interests lie in computer vision, generative models, and human-centered AI. More specifically, I’m passionate about modeling and understanding human motion for applications in video and 3D generation, biomechanics, and embodied agents.

Email / Scholar / Github / Linkedin / X

news

Nov, 2025 SocialGen is accepted to 3DV 2026.
Sep, 2025 I’ll be joining UPenn GRASP Lab as a research intern.
Feb, 2025 The Language of Motion is accepted to CVPR 2025.
Jun, 2024 I’ll be joining Stanford Vision and Learning Lab as a research intern.

selected publications

  1. Under Review
    humanscore.png
    HumanScore: Benchmarking Human Motions in Generated Videos
    Yusu Fang*, Tiange Xiang*, Tian Tan, Narayan Schuetz, Scott Delp, Li Fei-Fei†, and Ehsan Adeli†
    Under Review , 2026
  2. 3DV
    socialgen.png
    SocialGen: Modeling Multi-Human Social Interaction with Language Models
    Heng Yu*, Juze Zhang*, Changan Chen, Yusu Fang, Tiange Xiang, Juan Carlos Niebles, and Ehsan Adeli
    In International Conference on 3D Vision (3DV) , 2026
    arXiv PDF Website
  3. CVPR
    lom.png
    The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion
    Changan Chen*, Juze Zhang*, Shrinidhi K. Lakshmikanth*, Yusu Fang, Ruizhi Shao, Gordon Wetzstein, Li Fei-Fei, and Ehsan Adeli
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2025
    arXiv PDF Code Website