Jiyue Zhu

也无风雨也无晴

Robotics enthusiast
La Jolla, CA, US
jiyuezhu@ucsd.edu

About Me

Hi there!

I am a master's student in Computer Science and Engineering at the University of California, San Diego, working with Prof. Xiaolong Wang. I completed my Bachelor's degree in Computer Science at the University of Michigan, Ann Arbor, and I also received a Bachelor's degree in Electrical and Computer Engineering from Shanghai Jiao Tong University. Throughout my wonderful undergraduate academic life, I was fortunate to work with Prof. Odest Chadwicke Jenkins and Prof. Jie Liu.

My research interests lie at the intersection of robotics and machine learning, with a focus on dexterous manipulation, reinforcement learning, and imitation learning. Apart from these, I have a wide-ranging interest in cryptography and algorithms.

Education

Sept. 2023 - Jun. 2025 (expected)
Master of Science in Computer Science and Engineering
University of California-San Diego, La Jolla, CA, United States
Sept. 2021 - Apr. 2023
Bachelor of Science in Engineering in Computer Science, Summa Cum Laude
University of Michigan-Ann Arbor, Ann Arbor, MI, United States
Sept. 2019 - Aug. 2023
Bachelor of Science in Electrical and Computer Engineering
Shanghai Jiao Tong University, Shanghai, China
Sept. 2016 - Jun. 2019
High School
No. 2 High School of East China Normal University, Shanghai, China

Interests

Robot Learning
Dexterous Manipulation
Robotics Perception and Locomotion
Computer Vision

Awards & Scholarships

Winter 2022 College of Engineering - Dean's List, UMich
Apr. 2022
Winter 2022 University Honors, UMich
Apr. 2022
Fall 2021 College of Engineering - Dean's List, UMich
Dec. 2021
Fall 2021 University Honors, UMich
Dec. 2021
2020 VEX World Championship China Finals VEX U Division, Champion, Excellence Award, Robot Skills Challenge Champion
2020
2019-2020 Undergraduate Excellent Scholarship, Third Prize, SJTU
2020
2020 Interdisciplinary Contest in Modeling, Successful Participant
2020

Selected Research

ManiFlow: A Dexterous Manipulation Policy using Flow Matching
Ge Yan, 
Jiyue Zhu, 
Yuquan Deng, 
Shiqi Yang, 
Ri-Zhao Qiu, 
Xuxin Cheng, 
Marius Memmel, 
Ranjay Krishna, 
Ankit Goyal, 
Xiaolong Wang, 
Dieter Fox
May 1st 2025
In submission to CoRL 2025
#Dexterous Manipulation
#Imitation Learning
#Flow Matching

An advanced flow matching model specifically designed to support dexterous manipulation tasks.

Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation
Jianglong Ye, 
Keyi Wang, 
Chengjing Yuan, 
Ruihan Yang, 
Yiquan Li, 
Jiyue Zhu, 
Yuzhe Qin, 
Xueyan Zou, 
Xiaolong Wang
Apr 1st 2025
RSS 2025
#Dexterous Manipulation
#Demonstration Generation

A large-scale dataset of one billion diverse and high-quality dexterous manipulation demonstrations, generated using a constraint-aware generative model.

Object Pose Estimation through Dexterous Touch
Amir Hossein Shahidzadeh*, 
Jiyue Zhu*, 
Kezhou Chen, 
Sha Yi, 
Cornelia Fermuller, 
Yiannis Aloimonos, 
Xiaolong Wang
Mar 1st 2025
In submission to IROS 2025
#Reinforcement Learning
#Tactile Sensing

An RL framework to estimate object pose using only tactile sensing and proprioception.

Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning
Runyu Ding*, 
Yuzhe Qin*, 
Jiyue Zhu*, 
Chengzhe Jia, 
Shiqi Yang, 
Ruihan Yang, 
Xiaojuan Qi, 
Xiaolong Wang
Jul 3rd 2024
In submission to IROS 2025
#Teleoperation
#Imitation Learning

A real-time bimanual dexterous robot teleoperation system for imitation learning.

arXiv
Webpage
Last Updated on May 5th 2025