S. Lester Li

Contact: sizheli [at] mit [dot] edu

prof_pic.jpg

I am a PhD student at MIT CSAIL working with Vincent Sitzmann and Josh Tenenbaum. Previously, I completed my B.S. in Computer Science at the University of Rochester. My research is partly supported by the MIT Presidential Fellowship.

I am interested in building inverse models that capture the rich and structured representation of the physical world from unstructured observation. To this end, my research draws ideas from vision+graphics, robotics, and computational cognitive science.

To master/undergraduate students: If you would like to chat about life, career, or AI/ML research, feel free to email me. I encourage students from underrepresented groups to reach out and will prioritize replying to these messages.

News

Jul 15, 2024 Check out our new preprint on learning representation of robotic embodiment!

Publications

  1. arXiv
    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
  2. CVPR
    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
    Oral Presentation, Best Paper Runner Up
  3. ICLR
    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
  4. ICLR
    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