Jinzhou Li

I am a second-year Ph.D. student in Robotics at Duke University, advised by Prof. Xianyi Cheng. My research interests include large-scale reinforcement learning, dexterous manipulation, and multisensory learning with tactile and force sensing.

Before Duke, I worked with Prof. Hao Dong at Peking University. I completed my master's at Cornell University, advised by Prof. Maha Haji and Prof. Daniel Hastings, and earned my bachelor's degree from the University of Vermont. I have also spent time at AGIBOT (2024-2025) and Amazon Robotics (2026).

jinzhou

News

10.2026

Released ReDex, which improves sim-to-real dexterous policies through finger-level human corrections.

05.2026

Joined Amazon Robotics as an Applied Scientist Intern in the Bay Area for summer 2026.

05.2026

Co-organized the Workshop on Manipulation Robustness at ICRA 2026.

12.2025

Released OpenTouch, a benchmark for full-hand tactile sensing in the wild.

Selected Publications

* equal contribution

2026

ReDex: Repairing Sim-to-Real Dexterous Policies by Finger-Level Compliant Interaction

Jinzhou Li, Hadi Tabatabaee, Kelin Yu, Yuyin Sun, Cheng-Hao Kuo, Roberto Martín-Martín, Nima Fazeli, Alice Wu, Xianyi Cheng
CoRL 2026 Workshop on Learning from Corrections and Interventions
arXiv 2026
Webpage  •   Paper

OpenTouch: Bringing Full-Hand Touch to Real-World Interaction

Yuxin Ray Song*, Jinzhou Li*, Rao Fu*, Devin Murphy, Kaichen Zhou, Rishi Shiv, Yaqi Li, Haoyu Xiong, Crystal Elaine Owens, Yilun Du, Yiyue Luo, Xianyi Cheng, Antonio Torralba, Wojciech Matusik, Paul Pu Liang
arXiv 2026
Webpage  •   Paper   •   Code

CoPRE proprioceptive contact detection for low-cost robot arms

CoPRE: Improving Sensitivity in Proprioceptive Contact Detection for Low-Cost Robot Arms

Yuxiao Zhu*, Jinzhou Li*, Yifei Dong, Muhammad Suhail, Chunyuan Yang, Xinyuan Luo, Haoyu Li, Boyuan Chen, Xianyi Cheng
RSS 2026 Workshop on Planning and Control with Imperfect Sensors and Perception
In submission

Any-ttach interchangeable end-effectors and tools

Any-ttach: Quick End-effector Swapping Enables Manipulation Dexterity with Simplicity

Weizhe Ni*, Jinzhou Li*, Haoyu Li, Wenjing Pan, Cody Andres Alessio-Bunnell, Xianyi Cheng
RSS 2026 Workshop on Dexterous Manipulation: Scalable Learning for Human-Level Skills
arXiv 2026
Webpage  •   Paper

HiPolicy

HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning

Jiyao Zhang, Zimu Han, Junhan Wang, Xionghao Wu, Shihong Lin, Jinzhou Li, Hongwei Fan, Ruihai Wu, Dongjiang Li, Hao Dong
ECCV 2026
Webpage  •   Paper

2025
twinaligner

TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulation

Hongwei Fan*, Hang Dai*, Jiyao Zhang*, Jinzhou Li, Qiyang Yan, Yujie Zhao, Mingju Gao, Jinghang Wu, Hao Tang, Hao Dong
arXiv 2025
Webpage  •   Paper   •   Code

SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training

Mingdong Wu*, Lehong Wu*, Yizhuo Wu*, Weiyao Huang, Hongwei Fan, Zheyuan Hu, Haoran Geng, Jinzhou Li, Jiahe Ying, Long Yang, Yuanpei Chen, Hao Dong
IROS 2025
Webpage  •   Paper

AdapTac-Dex: Adaptive Visuo-Tactile Fusion with Predictive Force Attention for Dexterous Manipulation

Jinzhou Li*, Tianhao Wu*, Jiyao Zhang**, Zeyuan Chen**, Haotian Jin, Mingdong Wu, Yujun Shen, Yaodong Yang, Hao Dong
IROS 2025
Webpage  •   Paper   •   Code

clutterdexgrasping

ClutterDexGrasp: A Sim-to-Real System for General Dexterous Target Grasping in Cluttered Scenes

Zeyuan Chen*, Qiyang Yan*, Yuanpei Chen*, Tianhao Wu, Jiyao Zhang, Zihan Ding, Jinzhou Li, Yaodong Yang, Hao Dong
CoRL 2025Oral
Webpage  •   Paper

3DTac-Dex

3DTac-Dex: Canonical Representation and Force-Based Pretraining of 3D Tactile for Dexterous Visuo-Tactile Policy Learning

Tianhao Wu, Jinzhou Li*, Jiyao Zhang*, Mingdong Wu, Hao Dong
ICRA 2025
Webpage  •   Paper   •   Code

Teaching

Fall 2026 ME 344L-002: Control of Dynamic Systems Teaching Assistant, Duke University
Fall 2023 CS 4782: Introduction to Deep Learning Teaching Assistant, Cornell University

Projects

FR3 Stack

A Python library for the Franka FR3 robot, supporting hybrid force control.

Webpage  •   Code

Service

Conference Reviewer: ICRA 24–27; IROS 2026; NeurIPS 2026

Journal Reviewer: IEEE Robotics and Automation Letters (RA-L)

Workshop Organizer: Workshop on Manipulation Robustness at ICRA 2026