XYZ@XYZ-99
Curiosity about the entire universe.
  null   xuyinzhen.hiPlease don't spam me,@Thank you please.gmail.com   https://github.com/XYZ-99   NVIDIA

About

I am Yinzhen Xu, a research engineer at NVIDIA, working with Dr. Jim Fan and Prof. Yuke Zhu on the GEAR team building generalist robot and embodied agent foundation models. I received my master's degree from UC San Diego and my bachelor's degree from Peking University, where I was advised by Prof. He Wang. I am interested in building intelligent systems that can interact with the real world to benefit people's lives, and am currently working on embodied AI, robotics, and robot learning.

Publications

NitroGen NitroGen: An Open Foundation Model for Generalist Gaming Agents
L Magne, A Awadalla, G Wang, Yinzhen Xu, J Belofsky, F Hu, J Kim, L Schmidt, et al.
CVPR 2026 (Best Paper Honorable Mention)

An open vision-action foundation model for generalist gaming agents, trained via behavior cloning on 40,000+ hours of internet gameplay across 1,000+ games — generalizing to unseen games out of the box.
GR00T N1 GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
J Bjorck, F Castañeda, N Cherniadev, X Da, R Ding, L Fan, Y Fang, D Fox, … Yinzhen Xu, et al. (NVIDIA GEAR Team)
Whitepaper 2025

An open, customizable Vision-Language-Action foundation model for generalist humanoid robots, trained on a heterogeneous mixture of real-robot trajectories, human videos, and synthetically generated data.
FLARE FLARE: Robot Learning with Implicit World Modeling
R Zheng, J Wang, S Reed, J Bjorck, Y Fang, F Hu, J Jang, K Kundalia, Yinzhen Xu, et al.
arXiv 2025

A simple add-on that aligns a diffusion-transformer policy's features with latent embeddings of future observations, letting VLA models anticipate the future and even co-train on action-free human video.
DreamGen DreamGen: Unlocking Generalization in Robot Learning through Neural Trajectories
J Jang, S Ye, Z Lin, J Xiang, J Bjorck, Y Fang, F Hu, S Huang, K Kundalia, Yinzhen Xu, et al.
arXiv 2025

A 4-stage pipeline that turns video world models into "neural trajectories" — synthetic robot data — to unlock behavior and environment generalization from just a single teleoperated task.
UniDexGrasp UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
Yinzhen Xu*, Weikang Wan*, Jialiang Zhang*, Haoran Liu*, Zikang Shan, Hao Shen, Ruicheng Wang, Haoran Geng, Yijia Weng, Jiayi Chen, Tengyu Liu, Li Yi, He Wang†
CVPR 2023

We tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting.
DexGraspNet DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation
Ruicheng Wang*, Jialiang Zhang*, Jiayi Chen, Yinzhen Xu, Puhao Li, Tengyu Liu, He Wang†
ICRA 2023

We present a large-scale robotic dexterous grasp dataset, DexGraspNet, generated by our proposed highly efficient synthesis method that can be generally applied to any dexterous hand.
HOTrack Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild
Jiayi Chen*, Mi Yan*, Jiazhao Zhang, Yinzhen Xu, Xiaolong Li, Yijia Weng, Li Yi, Shuran Song, He Wang†
AAAI 2023 (Oral Presentation)

In this work, we tackle the challenging task of jointly tracking hand object pose and reconstructing their shapes from depth point cloud sequences in the wild, given the initial poses at frame 0.

Experience

NVIDIA
Research Engineer
Jul 2024 – Present
Research engineer at GEAR, working with Dr. Jim Fan and Prof. Yuke Zhu on generalist foundation models for robotics and embodied agents.
NVIDIA
Research Intern
Oct 2023 – Dec 2023
Research intern with Dr. Jim Fan at the Embodied Agents Group.
BIGAI
Beijing, China
Research Intern
Aug 2021 – Aug 2022
Research intern at the Beijing Institute for General Artificial Intelligence, working on robotics and dexterous grasping with Prof. He Wang.
Peking University
Beijing, China
Research Intern
Jun 2020 – Feb 2021
Worked on 3D vision and scene reconstruction.

Education

UC San Diego
La Jolla, CA
M.S. in Computer Science
Sep 2022 – Mar 2024
Peking University
Beijing, China
B.S. in Computer Science
Sep 2018 – Jul 2022

Blog.