Publications
For the most up-to-date list, see my Google Scholar.
(Co-)First Author
-
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
* Co-first authors · ‡ Project lead · § Equal contribution · † Amazon FAR Team Co-Lead
Tech Report, June 2026
-
Learning Dexterous Manipulation Skills from Imperfect Simulations
* Equal contribution (listed in alphabetical order). · † Equal advising.
IEEE International Conference on Robotics & Automation (ICRA), 2026
-
MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning
∗ Equal Contribution · † Equal Advising
International Conference on Learning Representations (ICLR), 2026 Oral (Top 1%)
-
Coordinated Humanoid Manipulation with Choice Policies
* Equal contribution. † Equal advising.
Tech Report, December 2025
-
Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies
*Equal contribution
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
-
Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning
∗ Equal contribution. Project Co-lead. · † Corresponding Author.
Robotics: Science and Systems (RSS), 2024 Best Paper Award Finalist
-
Prompt a Robot to Walk with Large Language Models
-
DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment
∗ Equal contribution, listed alphabetically. · † Corresponding author.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
-
Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer
∗ Equal contribution. Listed alphabetically.
Other Contributions
-
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
* indicates equal contributions · † indicates corresponding authors
International Conference on Machine Learning (ICML), 2025 Spotlight
-
Improving Vision-Language-Action Model with Online Reinforcement Learning
∗ Equal contribution · † Corresponding author.
IEEE International Conference on Robotics & Automation (ICRA), 2025
-
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
*Equal Contribution
-
HuB: Learning Extreme Humanoid Balance
*Equal Contribution
Conference on Robot Learning (CoRL), 2025
-
HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers
* These authors contributed equally to this work. · † Corresponding author.
Conference on Robot Learning (CoRL), 2024
-
Prediction with Action: Visual Policy Learning via Joint Denoising Process
∗ Equal contribution. · † Corresponding author.
Advances in Neural Information Processing Systems (NeurIPS), 2024
-
Decentralized Motor Skill Learning for Complex Robotic Systems
∗ Equal contribution.
IEEE Robotics and Automation Letters (RA-L), 2023
-
Evolution of Humanoid Locomotion Control
⋆ These authors contributed equally to this work. · † Corresponding authors.
Survey, 2025