Alex Z. Yin

CS PhD @ UC Berkeley EECS

Alex Zhao-Heng Yin

I am a CS Ph.D. student at BAIR, UC Berkeley.
I research robotics and AI.

Make Robots Work

We explore new ideas for creating intelligent robotic systems that learn to serve and enhance human lives. We value the elegance of intelligence and are driven by the excitement of tackling the most complex challenges.

Robot Brain Research

Our mission is to develop scalable systems for building the robot brain.
Objects, Motions, Actions. We study the mind's atoms that shape our world.

Selected Works

Object-centric 3D Motion Field for Robot Learning from Human Videos

Zhao-Heng Yin, Sherry Yang, Pieter Abbeel

Tech Report 2025

PDF Project

Dexterity Gen: Foundation Controller for Unprecedented Dexterity

Zhao-Heng Yin, Changhao Wang, Luis Pineda, Francois Hogan, Krishna Bodduluri, Akash Sharma, Patrick Lancaster, Ishita Prasad, Mrinal Kalakrishnan, Jitendra Malik, Mike Lambeta, Tingfan Wu, Pieter Abbeel, Mustafa Mukadam

Robotics: Science and Systems (RSS) 2025

PDF Project

Geometric Retargeting: A Principled, Ultrafast Neural Hand Retargeting Algorithm

Zhao-Heng Yin, Changhao Wang, Luis Pineda, Krishna Bodduluri, Tingfan Wu, Pieter Abbeel, Mustafa Mukadam.

International Conference on Intelligent Robots and Systems (IROS) (Oral) 2025

PDF Project Code

Offline Imitation Learning through Graph Search and Retrieval

Zhao-Heng Yin, Pieter Abbeel

Robotics: Science and Systems (RSS) 2024

PDF Project

Twisting Lids off with Two Hands

Toru Lin*, Zhao-Heng Yin*, Haozhi Qi, Pieter Abbeel, Jitendra Malik

Conference on Robot Learning (CoRL) 2024

PDF Project Code

Rotating without Seeing: Towards In-hand Dexterity through Touch

Zhao-Heng Yin*, Binghao Huang*, Yuzhe Qin, Qifeng Chen, Xiaolong Wang

Robotics: Science and Systems (RSS) 2023

PDF Project Code

Spatial Generalization of Visual Imitation Learning with Position-Invariant Regularization

Zhao-Heng Yin, Yang Gao, Qifeng Chen

Robotics: Science and Systems (RSS) Workshop 2023

PDF Code

Planning for Sample Efficient Imitation Learning

Zhao-Heng Yin, Weirui Ye, Qifeng Chen, Yang Gao

Neural Information Processing Systems (NeurIPS) 2022

PDF Code

Cross Domain Robot Imitation with Invariant Representation

Zhao-Heng Yin, Lingfeng Sun, Hengbo Ma, Masayoshi Tomizuka, Wu-Jun Li

International Conference on Robotics and Automation (ICRA) 2022

PDF Code

Diverse Critical Interaction Generation for Planning and Planner Evaluation

Zhao-Heng Yin*, Lingfeng Sun*, Liting Sun, Masayoshi Tomizuka, Wei Zhan

International Conference on Intelligent Robots and Systems (IROS) 2021

PDF

TOMA: Topological Map Abstraction for Reinforcement Learning

Zhao-Heng Yin, Wu-Jun Li

Tech Report 2020

PDF

Biography

Nanjing - Hong Kong - San Francisco

- B.S. CS, Mathematics. Nanjing University.

- M.Phil. EE. HKUST Robotics Institute.

- Ph.D. CS. UC Berkeley EECS.

During high school (N.S.F.Z.), I studied humanities.

I am advised by Pieter Abbeel.

E-mail: zhaohengyin (at) cs.berkeley.edu

Copyright © 2025 Zhao-Heng Yin