Yunhao Cao

🐟

Yunhao Cao

PhD Student

Cornell University

About Me

I am a Ph.D. student at Cornell CIS advised by Prof. Kuan Fang. My research interest is to develop sample-efficient robot learning methods to acquire robust and versatile behaviors. I obtained my Bachelor’s degree from UC Berkeley. During my time there as an undergraduate student, I was fortunate enough to have worked with Laura Smith, Prof. Sergey Levine, and Dr. Allen Yang.

Interests

Artificial Intelligence
Robot Learning

Education

PhD Computer Science
Cornell University
BA Computer Science
UC Berkeley

Featured Publications

Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration

Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration

We present CorDex, a framework that robustly learns dexterous functional grasps of novel objects from synthetic data generated from just a single human demonstration video through correspondence-based transfer and optimization.

Jan 7, 2026

Correspondence-Oriented Imitation Learning: Flexible Visuomotor Control with 3D Conditioning

Correspondence-Oriented Imitation Learning: Flexible Visuomotor Control with 3D Conditioning

We propose a method for learning robot manipulation policies in a self-supervised manner using a flexible 3D-based task representation.

Oct 30, 2025

Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion

Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion

We propose a method for dynamically adjusting a robot’s exploration while learning in the real world. We demonstrate that growing the limits of the robot’s search space leads to safer, more efficient learning and enables continuous improvement.

May 13, 2024

Recent Publications

Xingyi He, Adhitya Polavaram, Yunhao Cao, Om Deshmukh, Tianrui Wang, Xiaowei Zhou, Kuan Fang. Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration. In ArXiv, 2026.

PDF Cite Website

Yunhao Cao, Zubin Bhaumik, Jessie Jia, Xingyi He, Kuan Fang. Correspondence-Oriented Imitation Learning: Flexible Visuomotor Control with 3D Conditioning. In ArXiv, 2025.

PDF Cite Website

Laura Smith, Yunhao Cao, Sergey Levine. Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion. In ICRA2024, 2024.

PDF Cite Code Video Website