Yunzhu Li

Yunzhu Li

I am an Assistant Professor of Computer Science at Columbia University.

Before joining Columbia, I was an Assistant Professor at UIUC CS. I also spent time as a Postdoc at the Stanford Vision and Learning Lab (SVL), working with Fei-Fei Li and Jiajun Wu. I received my PhD from the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, where I was advised by Antonio Torralba and Russ Tedrake, and I obtained my bachelor's degree from Peking University.

/ / / yunzhu.li [at] columbia (dot) edu

At RoboPIL, we work at the intersection of robotics, computer vision, and machine learning. Specifically, we focus on Robot Learning and aim to significantly expand robots' perception and physical interaction capabilities, particularly through the following three directions.
- Structured World Models: Learning physics-inspired predictive models from and for robotic manipulation of deformable objects.
- Embodied Intelligence: Developing and integrating robotic foundation models for generalizable and long-horizon embodied interactions.
- Multi-Modal Perception: Harnessing vision, touch, audio, and language for fine-grained and effective manipulation.
Prospective Students: I'm looking for technically strong and self-motivated students passionate about advancing the frontiers of robot learning.
- PhD Applicants: Please submit your application to the CS PhD program, and mention me as one of your Faculty of Interest.
- Postdoc and Visiting Students: Please reach out to me directly via email, attaching your CV.

PhD Students

Binghao Huang

Hanxiao Jiang

Shivansh Patel

Yixuan Wang

Kaifeng Zhang

Master's and Undergraduate Students
- Baoyu Li (CS Master, with Kris Hauser)
- Keyi Shen (ECE Master, with Huan Zhang)
- Guang Yin (ECE Master)
- Jiangwei Yu (CS Master, with Huan Zhang)
- Shuo "Chris" Sha (CS Undergrad)
- Yolanda Zhu (CS Undergrad)

Foundation Models for Robotic Manipulation
[2024/03] Invited Talk, CMU VASC Seminar

Learning Structured World Models From and For Physical Interactions
[2024/03] Guest Lecture, CMU 16-831: Intro to Robot Learning

[2024/11] Invited Talk at UPenn GRASP Seminar
[2024/11] Invited Talk at CoRL 2024 Workshop on Differentiable Optimization Everywhere
[2024/11] Invited Talk at Next-Gen Robot Learning Symposium at TU Darmstadt
[2024/09] Invited Talk at Allerton Conference on Communication, Control, and Computing
[2024/08] Invited Talk at TTIC Summer Workshop on Multimodal Artificial Intelligence
[2024/07] Invited Talk at RSS 2024 Workshop on Structural Priors as Inductive Biases for Learning Robot Dynamics
[2024/07] Invited Talk at RSS 2024 Workshop on Koopman Operators in Robotics
[2024/06] Invited Talk at Boston Dynamics AI Institute
[2024/05] Invited Talk at ICRA 2024 Workshop on A Future Roadmap for Sensorimotor Skill Learning for Robot Manipulation
[2024/05] Invited Talk at ICRA 2024 Workshop on Bimanual Manipulation: On Kitchen Challenges
[2024/03] Invited Talk at CMU Robotics Institute, VASC Seminar [Recording]
[2024/03] Guest Lecture for 16-831: Introduction to Robot Learning at CMU [Recording]
[2024/03] Invited Talk at AICE Spring Research Symposium
[2024/01] Invited Talk at Mila Robot Learning Seminar [Recording]

Teachers Ranked as Excellent at UIUC, Spring 2024 [Link]
Best Conference Paper Award, International Conference on Robotics and Automation (ICRA) 2024 [Link]
Sony Faculty Innovation Award, 2023 [Link]
Best Systems Paper Award, Conference on Robot Learning (CoRL) 2023 [Link]
Finalist, Best Paper/Best Student Paper Awards, Conference on Robot Learning (CoRL) 2023 [Link]
First Place Recipient, Ernst A. Guillemin Master's Thesis Award in Artificial Intelligence and Decision Making at MIT, 2021 [Link]
Finalist, Facebook Fellowship, 2021 [Link]
Finalist, NVIDIA Graduate Fellowship, 2019, 2020, 2021 [Link]
Outstanding Reviewer, ICCV 2021 [Link]
Adobe Research Fellowship, 2020 [Link]
Outstanding Undergraduate Thesis Award, EECS Dept., Peking Univ. (10 in 400)