Soomin Park

prof_pic.png
sumny[at]kaist.ac.kr

I am a Ph.D. candidate at the Lifelike Avatar & Agent Laboratory, KAIST, advised by Prof. Sung-Hee Lee. I received my M.S. from the same laboratory.

My research interests lie in generative modeling for human motion, spanning both kinematic and physics-based approaches. I am currently developing humanoid control methods that enable flexible motion adaptation across diverse tasks and whole-body control with dexterous hands for precise object interaction. My research goal is to contribute to advancements and applications in computer animation, robotics, and AR/VR.

I’m always happy to chat about research or potential collaborations. Please feel free to reach out!

CV | Google Scholar | Github | LinkedIn

news

Aug, 2026 I’ll be joining in Roblox as a research intern (Aug–Dec 2026), hosted by Mubbasir Kapadia.
Apr, 2026 MaskAdapt has been selected as a Highlight paper at CVPR 2026.
Feb, 2026 MaskAdapt has been accepted to CVPR 2026.

publications

  1. CVPR
    park2026maskadapt.jpg
    MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters
    Soomin Park, Eunseong Lee, Kwang Bin Lee, and Sung-Hee Lee
    CVPR 2026 🏆 Highlight Paper (top 3.6% of submissions)
    arXiv PDF Project
  2. TOG
    jang2022motion.jpg
    Motion Puzzle: Arbitrary Motion Style Transfer by Body Part
    Deok-Kyeong Jang, Soomin Park, and Sung-Hee Lee
    ACM Transactions on Graphics (Proc. SIGGRAPH) 2022
    arXiv PDF Code Project
  3. PACMCGIT
    park2021diverse.jpg
    Diverse Motion Stylization for Multiple Style Domains via Spatial-Temporal Graph-Based Generative Model
    Soomin Park, Deok-Kyeong Jang, and Sung-Hee Lee
    Proceedings of the ACM on Computer Graphics and Interactive Techniques (Proc. SCA) 2021
    PDF Code Project