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
(w/ Shenlong Wang)

Shivansh Patel

Rhythm Syed
(w/ Tony Dear)

Yixuan Wang

Kaifeng Zhang

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

Towards General Robotic Intelligence
[2025/03] Invited Talk, Columbia AI Summit

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

Structured World Models for Manipulation
[2024/03] Guest Lecture, CMU 16-831

[2025/06] Invited Talk at CVPR 2025 Workshop on 3D Vision Language Models (VLMs) for Robotics Manipulation
[2025/06] Invited Talk at CVPR 2025 Workshop on Generalization in Robotics Manipulation Workshop and Challenges
[2025/05] Invited Talk at ICRA 2025 Workshop on Foundation Models and Neuro-Symbolic AI for Robotics
[2025/05] Invited Talk at ICRA 2025 Workshop on Reflections on Representations and Manipulating Deformable Objects
[2025/05] Invited Talk at ICRA 2025 Workshop on Structured Learning for Efficient, Reliable and Transparent Robots
[2025/04] Invited Talk at Princeton University
[2025/04] Guest Lecture at 16-831: Introduction to Robot Learning at CMU
[2025/03] Invited Talk at Google DeepMind
[2025/03] Invited Talk at UMich Robotics Seminar
[2025/03] Invited Talk at Columbia AI Summit [Recording]
[2025/02] Invited Talk at Samsung Research
[2025/02] Talks at AAAI 2025 Tutorial on Foundation Models Meet Embodied Agents [Recording] and New Faculty Highlights
[2025/02] Guest Lecture at COMS 6113: Agentic Systems Made Real at Columbia University
[2025/02] Invited Talk at NYC Computer Vision Day

AAAI New Faculty Highlights, 2025 [Link]
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)