Photo credit to Sijia Xiao.

I am a third-year Ph.D. Candidate at Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, advised by Prof. Antonio Torralba and Prof. Russ Tedrake. Before coming to MIT, I received the B.S. in Computer Science from Peking University in 2017.

My research interests lie in computer vision, machine learning, and robotics. In particular, I am interested in how we can enable better robotic manipulation skills via dynamics modeling and multimodal perception.



(* indicate equal contribution)

Yunzhu Li*, Hao He*, Jiajun Wu, Dina Katabi, and Antonio Torralba
Learning Compositional Koopman Operators for Model-Based Control
ICLR 2020, [Project] [Paper] [BibTex]
Spotlight Presentation
Abridged in NeurIPS 2019 workshop on Graph Representation Learning [Link]

Kexin Yi*, Chuang Gan*, Yunzhu Li, Pushmeet Kohli, Jiajun Wu, Antonio Torralba, and Joshua B. Tenenbaum
CLEVRER: Collision Events for Video Representation and Reasoning
ICLR 2020, [Project] [Paper] [BibTex]
Spotlight Presentation

Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B. Tenenbaum, and Antonio Torralba
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
ICLR 2019, [Project] [PDF] [Code] [BibTex] [Poster] [Video]
Covered by [MIT News] [Engadget] [NVIDIA Developer]

Yunzhu Li, Jiajun Wu, Jun-Yan Zhu, Joshua B. Tenenbaum, Antonio Torralba, and Russ Tedrake
Propagation Networks for Model-Based Control Under Partial Observation
ICRA 2019, [Project] [PDF] [Code] [BibTex] [Video]

Yunzhu Li, Jiaming Song, and Stefano Ermon
InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
NIPS 2017, [PDF] [Code] [BibTex] [Poster] [Video]

Yunzhu Li*, Benyuan Sun*, Tianfu Wu, and Yizhou Wang
Face Detection with End-to-End Integration of a ConvNet and a 3D Model
ECCV 2016, [PDF] [Code] [BibTex] [Poster]



Selected Honors

Professional Service


MIT Computer Science & Artificial Intelligence Lab
32 Vassar Street, 32-380
Cambridge, MA 02139
[Google Scholar] [Github]