𝐘𝐚𝐧𝐣𝐢𝐞 𝐙𝐞

Bachelor of Computer Science, Shanghai Jiao Tong Univeristy

I am doing research at Shanghai Qi Zhi Institute, focusing on intersection of Robotics, Reinforcement Learning, and Computer Vision. I work with Xiaolong Wang at University of California San Diego and Huazhe Xu at Tsinghua University.

I receive my Bachelor degree in Computer Science at Shanghai Jiao Tong University as Outstanding Graduate in June 2023. My bachelor thesis is Learning 3D Visual Representations for Robotic Manipulation, advised by Xiaolong Wang.

Feel free to contact me via email.

Research Interest

My focus is on learning generalizable {3D, 2D, language, dynamics} representations through {images, videos, texts, interaction data} for robotics. I like to explore the natural supervision signals from the data itself.

My aspiration is to drive advancements in the field of robotics and learning, with a focus on the following key perspectives:
(1) developing generalizable and effective learning algorithms under limited data conditions;
(2) achieving unprecedented robotic capabilities by learning;
(3) leveraging rich and diverse data and modern foundation models to empower embodied intelligence.

Publications

/ . Representative papers are highlighted.

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
Ruizhe Shi*, Yuyao Liu*, Yanjie Ze, Simon S. Du, Huazhe Xu
arXiv, 2023
project page / arXiv / code / bibtex
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Guowei Xu*, Ruijie Zheng*, Yongyuan Liang*, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu
arXiv, 2023
project page / arXiv / bibtex
H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
Yanjie Ze, Yuyao Liu*, Ruizhe Shi*, Jiaxin Qin, Zhecheng Yuan, Jiashun Wang, Huazhe Xu
Conference on Neural Information Processing Systems (NeurIPS), 2023
project page / arXiv / code / poster / bibtex
MoVie: Visual Model-Based Policy Adaptation for View Generalization
Sizhe Yang*, Yanjie Ze*, Huazhe Xu
Conference on Neural Information Processing Systems (NeurIPS), 2023
project page / arXiv / code / poster / bibtex
GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
Yanjie Ze*, Ge Yan*, Yueh-Hua Wu*, Annabella Macaluso, Yuying Ge, Jianglong Ye, Nicklas Hansen, Li Erran Li, Xiaolong Wang
Conference on Robot Learning (CoRL), 2023 (Oral)
project page / arXiv / code / poster / bibtex
On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
Nicklas Hansen*, Zhecheng Yuan*, Yanjie Ze*, Tongzhou Mu*, Aravind Rajeswaran+, Hao Su+, Huazhe Xu+, Xiaolong Wang+
International Conference on Machine Learning (ICML), 2023
arXiv / code / poster / bibtex
Visual Reinforcement Learning with Self-Supervised 3D Representations
Yanjie Ze*, Nicklas Hansen*, Yinbo Chen, Mohit Jain, Xiaolong Wang
Robotics and Automation Letters (RA-L), 2023
International Conference on Intelligent Robots and Systems (IROS), 2023 (Oral)
project page / arXiv / code / poster / bibtex
DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning
Canzhe Zhao*, Yanjie Ze*, Jing Dong, Baoxiang Wang, Shuai Li
International Joint Conference on Artificial Intelligence (IJCAI), 2023
arXiv / code / bibtex
Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization
Canzhe Zhao, Yanjie Ze, Jing Dong, Baoxiang Wang, Shuai Li
International Conference on Web Search and Data Mining (WSDM), 2023
arXiv / code / bibtex
UKPGAN: A General Self-Supervised Keypoint Detector
Yang You, Wenhai Liu, Yanjie Ze, YongLu Li, Weiming Wang, Cewu Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
project page / arXiv / code / bibtex

Recent Talks

Visual Representations for Generalizable Robotic Manipulation
November 2, 2023
Present at TechBeat, Shanghai AI Lab, and Tsinghua University.
slides / YouTube / Bilibili