S. Lester Li

Contact: sizheli [at] mit [dot] edu

prof_pic.jpg

I am a Computer Science PhD student at MIT CSAIL, advised by Vincent Sitzmann and Josh Tenenbaum. My research is supported by the MIT Presidential Fellowship.

I build the brains and bodies of robots. My research draws ideas from machine learning, physics, and cognitive AI, with applications in robotics, computer vision, and computer graphics.

Prospective students & visitors: Thank you for your interest! I strongly encourage students from underrepresented groups to reach out and will prioritize responding to these messages. For those interested in working with me, please email me your CV and highlight your favorite accomplishments, thanks!

News

Mar 23, 2025 Very excited to share my blog post on robot modeling and representation! A tutorial of Jacobian Fields with code. Looking forward to everyone’s feedbacks!
Jul 15, 2024 Check out our new preprint on learning representation of robotic embodiment!

Publications

  1. arXiv
    njf.gif
    Unifying 3D Representation and Control of Diverse Robots with a Single Camera
    Sizhe Lester Li, Annan Zhang, Boyuan Chen, Hanna Matusik, Chao Liu, Daniela Rus, and Vincent Sitzmann
    2024
    PAPER Code WEBSITE
  2. CVPR
    pixelsplat.gif
    pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
    David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann
    In the Computer Vision and Pattern Recognition Conference (CVPR), 2024
    Best Paper, Runners-Up
    PAPER Code WEBSITE
  3. ICLR
    dexdeform.gif
    DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics
    Sizhe Lester Li*, Zhiao Huang*, Tao Chen, Tao Du, Hao Su, Joshua B. Tenenbaum, and Chuang Gan
    In the International Conference on Learning Representations (ICLR), 2023
    PAPER Code WEBSITE
  4. ICLR
    cpdeform.gif
    Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics
    Sizhe Lester Li*, Zhiao Huang*, Tao Du, Hao Su, Joshua Tenenbaum, and Chuang Gan
    In the International Conference on Learning Representations (ICLR), 2022
    Spotlight Presentation
    PAPER Code