I am a Postdoc researcher at MIT CSAIL, working with Prof. Pulkit Agrawal and Prof. Edward Adelson. I earned my PhD degree from Shanghai Jiao Tong University, where I worked with Prof. Cewu Lu. My research focuses on General Robotic Manipulation.

Previously, I have spent time at Tencent YouTu Lab and the center for VCLA, UCLA, where I worked with Prof.Yu-Wing Tai and Prof.Song-Chun Zhu.

[Curriculum Vitae]

News

• 2024-10: Our Eyesight Hand paper has been selected as a Best RoboCup Paper Finalist at IROS 2024!
• 2024-09: One paper accepted to RA-L.
• 2024-06: Two papers accepted to IROS.
• 2024-05: Our RT-X paper won the Best Paper Award at ICRA 2024!
• 2024-01: Four papers accepted to ICRA.
• 2023-10: AnyGrasp won the Best Paper Award in IROS 2023 workshop “Learning Meets Model-based Methods for Manipulation and Grasping”!
• 2023-07: GraspNet-1Billion accepted to IJRR.
• 2023-06: One paper accepted to IROS.
• 2023-05: AnyGrasp accepted to T-RO.
• 2022-11: AlphaPose accpeted to T-PAMI.
• 2022-03: One paper accepted to Nature.
• 2021-06: Awarded the ByteDance Fellowship. Thanks ByteDance!
• 2020-11: Awarded the Microsoft Research Asia Fellowship. Thanks Microsoft!
• 2019-12: Awarded the Baidu Fellowship. Thanks Baidu!

Selected Publications

AnyDexGrasp: Learning General Dexterous Grasping for Different Hands with Human-level Efficiency

Hao-Shu Fang, Hengxu Yan, Zhenyu Tang, Hongjie Fang, Chenxi Wang, Cewu Lu

arXiv 2025  [paper][project]

EyeSight Hand: Design of a Fully-Actuated Dexterous Robot Hand with Integrated Vision-Based Tactile Sensors and Compliant Actuation

Branden Romero*, Hao-Shu Fang*, Pulkit Agrawal, Edward Adelson

IROS 2024 (Best RoboCup Paper Finalist)  [paper][project]

Causal Attention Enables Data-Efficient Generalizable Robotic Manipulation

Shangning Xia, Hongjie Fang, Cewu Lu, Hao-Shu Fang

ICRA 2025  [paper][project]

AirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wild

Hongjie Fang*, Hao-Shu Fang*, Yiming Wang*, Jieji Ren, Jingjing Chen, Ruo Zhang, Weiming Wang, Cewu Lu

ICRA 2024  [paper][project]

RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot

Hao-Shu Fang, Hongjie Fang, Zhenyu Tang, Jirong Liu, Chenxi Wang, Junbo Wang, Haoyi Zhu, Cewu Lu

ICRA 2024  [paper][project]

AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains

Hao-Shu Fang, Chenxi Wang, Hongjie Fang, Minghao Gou, Jirong Liu, Hengxu Yan, Wenhai Liu, Yichen Xie, Cewu Lu

IEEE Transactions on Robotics (T-RO), 2023  [paper][project]

Robust Grasping Across Diverse Sensor Qualities: The GraspNet-1Billion Dataset

Hao-Shu Fang, Minghao Gou, Chenxi Wang, Cewu Lu

The International Journal of Robotics Research (IJRR), 2023, also appeared on CVPR 2020 [CVF][project]

AlphaPose: Whole-body Regional Multi-person Pose Estimation and Tracking in Real-time

Hao-Shu Fang*,Jiefeng Li*, Hongyang Tang, Chao Xu, Haoyi Zhu, Yuliang Xiu, Yong-Lu Li, Cewu Lu

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022 [pdf][code]

For the full publication list please refer to my Google Scholar page.

Projects

GraspNet

General object grasping for any scenario

AlphaPose

Accurate multi-pereson pose estimation

Teaching

• Lecturer, 6.S186 Modern Robot Learning: Hands-on Tutorial, MIT, 2025
• Teaching Assistant, AI 1602 Introduction to Artificial Intelligence, SJTU, 2022
• Guest Lecturer, CS 386 Digital Image Processing, SJTU, 2020
• Teaching Assistant, AI 1602 Introduction to Artificial Intelligence, SJTU, 2020

Public Services

• Associate Editor for IROS 2025
• Co-chair for the IROS 2024 RoboCup Presentation session.
• Organizer for the ICML 2024 MFM-EAI Workshop.
• Reviewer for IJRR, T-RO, T-PAMI, IJCV, TMM, TOC, TIP, ICRA, IROS, ICLR, CVPR, ICCV, ECCV, AAAI, etc.