李忆唐Yitang Li | Stanford University

About Me

I am a first-year PhD student in Computer Science at Stanford University, working on robotics and embodied intelligence. Prior to Stanford, I received my B.E. from the Institute for Interdisciplinary Information Sciences (IIIS, Yao Class) at Tsinghua University, where I worked with Prof. Li Yi on character animation. During the Spring and Summer of 2025, I was a student intern at LeCAR Lab at Carnegie Mellon University, advised by Prof. Guanya Shi, where I worked on humanoid robot learning. Before university, I was a member of the Chinese national team for the Asian Physics Olympiad.

My primary research goal is to leverage large-scale human data to build generalizable robots capable of performing the full spectrum of human skills.

Beyond academics and research...

I am outgoing and curious, always eager to meet interesting people😊 and through them discover new perspectives on the world around me🌟. I have often taken the stage as a host, performer, and student representative speaker 🎤🎭 at major university events, and have served as class monitor and seminar organizer, supporting and connecting with my peers 🙋‍♀️. In my free time, I love writing (mostly essays✍️), singing 🎶, dancing 💃, keeping fit 🏋️, and traveling ✈️.

Research Interests

Character Animation🕺➡️🧠: Physics-based and interaction-centered motion synthesis; structured representations of human motion data
Robot Learning🧠➡️🤖: Humanoid robot learning and control; Scaleble skill learning from scalable data; Vision–language–action models

News

[Feb. 2026] BFM-Zero is accepted to ICLR 2026 ! See you in Brazil✨ And the Training Code is out! (ง ˙o˙)ว (๑˃̵ᴗ˂̵)و 😄
[Jan. 2026] BFM-Zero Inference Tutorial & Deployment 🚀 is out — try it, deploy it, and make it better 🛠️✨
[Dec. 2025] 🏆 Awarded the Presidential Scholarship of Tsinghua University (10 undergraduate recipients university-wide)
[Nov. 2025] Our paper BFM-Zero🛡️ is finally released🧘‍♂️! A unified skill space for zero-shot humanoid control across diverse🎨 tasks!
[Sep. 2025] Our paper HDMI is out🎬➡️🤖!
[Sep. 2025] I will be presenting Hold My Beer🍺 at CoRL 2025 in Seoul, South Korea!

Publications

ICLR

BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

Yitang Li*, Zhengyi Luo*, Tonghe Zhang$, Cunxi Dai$, Anssi Kanervisto, Andrea Tirinzoni, Haoyang Weng, Kris Kitani, Mateusz Guzek, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta†, Guanya Shi† (* Equal Contribution; $ Equal Contribution; † Equal Advising)

The International Conference on Learning Representations (ICLR), 2026.

PDF Code Project

CoRL

Hold My Beer🍻: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control

Yitang Li, Yuanhang Zhang, Wenli Xiao, Chaoyi Pan, Haoyang Weng, Guanqi He, Tairan He, Guanya Shi

Conference on Robot Learning (CoRL), 2025.

PDF Code Project

CVPR

Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References

Yitang Li*, Mingxian Lin*, Zhuo Lin, Yipeng Deng, Yue Cao, Li Yi (Equal Contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

PDF Code Project

In submission

HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos

Haoyang Weng, Yitang Li, Nikhil Sobanbabu, Zihan Wang, Zhengyi Luo, Tairan He, Deva Ramanan, Guanya Shi

PDF Code Project

ECCV

FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models

Zhikai Zhang, Yitang Li, Haofeng Huang, Mingxian Lin, Li Yi

European Conference on Computer Vision (ECCV), 2024.

PDF Project

In submission

EmbRACE3K: Embodied Reasoning and Action in Complex Environments

Mingxian Lin*, Wei Huang*, Yitang Li, Chengjie Jiang, Kui Wu, Fangwei Zhong, Shengju Qian, Xin Wang, Xiaojuan Qi

PDF Code Project

UAI

MutualNeRF: Improve the Performance of NeRF under Limited Samples with Mutual Information Theory

Zifan Wang*, Jingwei Li*, Yitang Li, Yunze Liu (Equal Contribution)

The Conference on Uncertainty in Artificial Intelligence, 2025.

PDF