Jim Fan
Co-leads NVIDIA's GEAR embodied-agents group; co-author of GR00T N1, Voyager and Eureka
Linxi "Jim" Fan co-leads NVIDIA's Generalist Embodied Agent Research (GEAR) group with Yuke Zhu; the group builds foundation models for embodied agents in virtual and physical worlds and lists GR00T, Eureka and Voyager among its projects. Fan's homepage describes a mission of building generally capable agents across robotics, games and simulation, and lists Voyager, MineDojo, Eureka and VIMA among Fan's research highlights; NVIDIA's research profile notes that MineDojo received an Outstanding Paper Award at NeurIPS 2022. Fan is a co-author of the GR00T N1 paper, which presents NVIDIA's open foundation model for generalist humanoid robots, and of the Isaac Lab technical report. Fan's homepage also notes a 2016 research internship at OpenAI.21345
Work
NVIDIA Isaac GR00T N1Published research
Listed among the authors of "GR00T N1: An Open Foundation Model for Generalist Humanoid Robots" (March 2025); GR00T appears among the GEAR group's projects.42
NVIDIA Isaac LabOpen-source code
Co-author of "Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning" (November 2025), the technical report the BSD-3-Clause Isaac Lab repository asks users to cite.56
Voyager and Eureka (external site: arxiv.org)Published research
Co-author of Voyager (2023), an LLM-powered agent that learns continually in Minecraft, and Eureka (2023), in which coding LLMs write reward functions for dexterous robot tasks; both appear among the research highlights on Fan's homepage.781
Other documented roles
Roles the sources document but that are not confirmed as current.
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.