𝐘𝐚𝐧𝐣𝐢𝐞 𝐙𝐞

I am a PhD student in Computer Science at Stanford University, working with Jiajun Wu. I am also affilated with the Stanford Vision and Learning Lab. My research centers around building embodied intelligence for general-purpose robots. Previously, I received my Bachelor degree in Computer Science at Shanghai Jiao Tong University, working with Xiaolong Wang and Huazhe Xu.

I am looking for self-motivated students who are extremely passionate about fundamental research in Humanoid Robot Learning/Dexterous Manipulation Learning/3D Robot Learning. If you are interested in working with me in our group, please directly send me an email with 1) your CV, 2) your research interests, and 3) why you are interested in working with me. For Stanford MS students and undergraduates, the minimum time commitment is 20 hours per week for 6 months. For visiting graduate students, the minimum length of a visit is 6 months. Longer time is surely preferred.

Some recent research highlights:

Improved 3D Diffusion Policy, arXiv 2024

Lipschitz-Constrained Policy, arXiv 2024

Visual Leg-Manipulation, IROS 2024


Publications

/ . Selected papers are highlighted.

Generalizable Humanoid Manipulation with Improved 3D Diffusion Policies
Yanjie Ze, Zixuan Chen, Wenhao Wang, Tianyi Chen, Xialin He, Ying Yuan, Xue Bin Peng, Jiajun Wu
arXiv, 2024
project page / arXiv / code (learning) / code (teleop) / bibtex
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
Yanjie Ze*, Gu Zhang*, Kangning Zhang, Chenyuan Hu, Muhan Wang, Huazhe Xu
Robotics: Science and Systems (RSS), 2024 (Oral)
project page / arXiv / code / 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