Tianyu Li

Tianyu Li 黎天宇

I am a Founding Research Scientist at Dexmate. I earned my Ph.D. in Computer Science from Georgia Tech. My research focuses on Agentic Robotics and Robot Whole-body Control.

There are a few folks that own the same name, such as Tianyu Li@MIT and Tianyu Li@UPENN, please make sure you contact the correct Tianyu Li.

Experience

Employment

Dexmate

Founding Research Scientist

Dexmate

2025 — Present

Meta

Researcher

FAIR @ Meta

2024

Facebook

Research Scientist

FAIR @ Facebook

2019 — 2021

Education

Georgia Tech

Ph.D. in Computer Science

Georgia Tech

Advisor: Prof. Sehoon Ha

Thesis: Cross-Embodiment Whole-Body Skill Imitation

2022 — 2025

CMU

M.S. in Computational Science

Carnegie Mellon University

Advisors: Prof. Hartmut Geyer, Prof. Chris Atkeson

2017 — 2018

Beihang University

B.E. in Energy and Power Engineering

Beihang University

2013 — 2017

Research

CVPR Findings, 2026

Switch-JustDance: Benchmarking Whole-Body Motion Tracking Policies Using a Commercial Console Game

Jeonghwan Kim*, Wontaek Kim*, Yidan Lu*, Jin Cheng*, Fatemeh Zargarbashi*, Zicheng Zeng*, Zekun Qi*, Zhiyang Dou, Nitish Sontakke, Donghoon Baek, Sehoon Ha, Tianyu Li

CoRL Workshop, 2025

Switch4EAI: Leveraging Console Game Platform for Benchmarking Robotic Athletics

Tianyu Li, Jeonghwan Kim, Wontaek Kim, Donghoon Baek, Seungeun Rho, Sehoon Ha

Arxiv, 2025

Learning Physical Interaction Skills from Human Demonstrations

Tianyu Li, Hengbo Ma, Sehoon Ha, Kwonjoon Lee

Arxiv, 2025

RobotMover: Learning to Move Large Objects by Imitating the Dynamic Chain

Tianyu Li, Joanne Truong, Jimmy Yang, Alexander Clegg, Akshara Rai, Sehoon Ha, Xavier Puig

ICLR, 2025

Language Guided Skill Discovery

Seungeun Rho, Laura Smith, Tianyu Li, Sergey Levine, Xue Bin Peng, Sehoon Ha

CVPR, 2024

AAMDM: Accelerated Auto-regressive Motion Diffusion Model

Tianyu Li, Zhuhan Qiao, Guanqiao Ren, KangKang Yin, Sehoon Ha

ICLR, 2024

CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning

Tianyu Li, Hyunyoung Jung, Matthew Gombolay, Yong Kwon Cho, Sehoon Ha

SIGGRAPH ASIA, 2023

ACE: Adversarial Correspondence Embedding for Cross Morphology Motion Retargeting from Human to Nonhuman Characters

Tianyu Li, Jungdam Won, Alexander Clegg, Jeonghwan Kim, Akshara Rai, Sehoon Ha

TWiLR
RSS, 2023

Learning and Adapting Agile Locomotion Skills by Transferring Experience

Laura Smith, J Chase Kew, Tianyu Li, Linda Luu, Xue Bin Peng, Sehoon Ha, Jie Tan, Sergey Levine

RA-L
RA-L, 2021

Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion

Tianyu Li, Roberto Calandra, Deepak Pathak, Yuandong Tian, Franziska Meier, Akshara Rai

ICRA 2020
ICRA, 2020

Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning

Tianyu Li, Nathan Lambert, Roberto Calandra, Franziska Meier, Akshara Rai

IROS 2020
IROS, 2020

Learning Navigation Skills for Legged Robots with Learned Robot Embeddings

Joanne Truong, Denis Yarats, Tianyu Li, Franziska Meier, Sonia Chernova, Dhruv Batra, Akshara Rai

CoRL 2019
CoRL, 2019

Bayesian Optimization in Variational Latent Spaces with Dynamic Compression

Rika Antonova, Akshara Rai, Tianyu Li, Danica Kragic

ATRIAS
ICRA, 2019

Using Deep Reinforcement Learning to Learn High-Level Policies on the ATRIAS Biped

Tianyu Li, Hartmut Geyer, Christopher G Atkeson, Akshara Rai