Linxi Fan
Researcher, NVIDIA
Joined
November 2019
Names
Linxi Fan (Preferred)
Emails
****@columbia.edu (Confirmed)
****@cs.stanford.edu (Confirmed)
****@nvidia.com (Confirmed)
Personal Links
Career & Education History
Researcher
NVIDIA (nvidia.com)
2021 – Present
PhD student
Stanford University (stanford.edu)
2016 – 2021
Undergrad student
Columbia University (columbia.edu)
2012 – 2016
Advisors, Relations & Conflicts
Expertise
computer vision
, representation learning
, video learning
2016 – Present
Publications
HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning and Adaptation
Kevin Lin, Ajay Mandlekar, Caelan Reed Garrett, Nikita Chernyadev, Yu Fang, Runyu Ding, Yuqi Xie, Linxi Fan, Yuke Zhu- Beyond Teleop workshop, ICRA 2026 Poster
- Readers: Everyone
HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning and Adaptation
Kevin Lin, Ajay Mandlekar, Caelan Reed Garrett, Nikita Chernyadev, Yu Fang, Runyu Ding, Yuqi Xie, Linxi Fan, Yuke Zhu- ICRA 2026 Workshop SDRL
- Readers: Everyone
SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation
Nadun Ranawaka Arachchige, Josiah Wong, Wei-Lin Pai, Wei-Teng Chu, Tianyuan Dai, Masoud Moghani, Hang Yin, Yunfan Jiang, Wesley Durbano, Brandon Bryce Huynh, Linxi Fan, Danfei Xu, Ruohan Zhang, Li Fei-Fei, Bowen Wen, Ajay Mandlekar, Yuke Zhu- Real2Sim2Real
- Readers: Everyone
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
Wenli Xiao, Haotian Lin, Andy Peng, Haoru Xue, Tairan He, Zhengyi Luo, Yuqi Xie, Fengyuan Hu, Linxi Fan, Guanya Shi, Yuke Zhu- ICLR 2026 Workshop RSI Spotlight
- Readers: Everyone
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
Wenli Xiao, Haotian Lin, Andy Peng, Haoru Xue, Tairan He, Zhengyi Luo, Yuqi Xie, Fengyuan Hu, Linxi Fan, Guanya Shi, Yuke Zhu- TTU at ICLR 2026 (Main)
- Readers: Everyone
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
Wenli Xiao, Haotian Lin, Andy Peng, Haoru Xue, Tairan He, Zhengyi Luo, Yuqi Xie, Fengyuan Hu, Linxi Fan, Guanya Shi, Yuke Zhu- ReALM-GEN 2026 - ICLR 2026 Workshop
- Readers: Everyone
World Action Models are Zero-shot Policies
Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng, Shenyuan Gao, Sihyun Yu, George Kurian, Suneel Indupuru, You Liang Tan, Chuning Zhu, Jiannan Xiang, Ayaan Naveed Malik, Kyungmin Lee, William Liang, Nadun Ranawaka Arachchige, Jiasheng Gu, Yinzhen Xu, Guanzhi Wang, Fengyuan Hu, Avnish Narayan, Johan Bjorck et al. (16 additional authors not shown)- ICLR 2026 Workshop World Models
- Readers: Everyone
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
Wenli Xiao, Haotian Lin, Andy Peng, Haoru Xue, Tairan He, Zhengyi Luo, Yuqi Xie, Fengyuan Hu, Linxi Fan, Guanya Shi, Yuke Zhu- ICLR 2026 Poster
- Readers: Everyone
DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
- CoRL 2025 Workshop Dexterous Manipulation Spotlight
- Readers: Everyone
SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning
- CoRL 2025 Robot Data Workshop
- Readers: Everyone
Co-Authors
- Aaron C. Courville
- Abhinav Shrivastava
- Adam Coates
- Agrim Gupta
- Ajay Mandlekar
- Anchit Gupta
- Andrej Karpathy
- Andrew Tang
- Andrew Tao
- Andrew Y. Ng
- Andy Peng
- Anima Anandkumar
- Animashree Anandkumar
- Antonio Torralba
- Avnish Narayan
- Awni Y. Hannun
- Ayaan Naveed Malik
- Billy Jun
- Bo Li
- Bo Xiao
- Bokui Shen
- Boris Ivanovic
- Bowen Wen
- Boyi Li
- Brandon Bryce Huynh