Will Liang
willjhliang@gmail.com (github, linkedin, gscholar, twitter, notes)
I am a PhD student at the University of California, Berkeley, advised by Pieter Abbeel and Jitendra Malik, and supported by the NSF Graduate Research Fellowship. My research interests include robot learning, generative models, and multimodal representations for embodied agents that learn from human priors and unstructured, self-directed experience.
I am also at Nvidia, with Joel Jang, Jim Fan, and Yuke Zhu. Previously, I studied at the University of Pennsylvania, with Jason Ma, Dinesh Jayaraman, Osbert Bastani, Kostas Daniilidis, and Jianbo Shi.
In the evenings, you might also find me playing guitar or painting.
Research
Selected representative publications are listed below. For the complete set, please see Google Scholar.
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
Shenyuan Gao*, William Liang*, Kaiyuan Zheng, Ayaan Malik, ..., Jun Zhang, Jitendra Malik, Pieter Abbeel, Ming-Yu Liu, Yuke Zhu†, Joel Jang†, Linxi "Jim" Fan†
Tether: Autonomous Play with Correspondence-Driven Trajectory Warping
William Liang, Sam Wang, Hung-Ju Wang, Osbert Bastani, Yecheng Jason Ma†, Dinesh Jayaraman†
International Conference on Learning Representations (ICLR), 2026
(coming soon!)
Eurekaverse: Environment Curriculum Generation via Large Language Models
William Liang, Sam Wang, Hung-Ju Wang, Osbert Bastani, Dinesh Jayaraman†, Yecheng Jason Ma†
Conference on Robot Learning (CoRL), 2024 (Oral)
DrEureka: Language Model Guided Sim-To-Real Transfer
Yecheng Jason Ma*, William Liang*, Hung-Ju Wang, Sam Wang, Yuke Zhu, Linxi "Jim" Fan, Osbert Bastani, Dinesh Jayaraman
Robotics: Science and Systems (RSS), 2024 (Oral)
Projects
The following are some other projects I particularly enjoyed. More can be found on Github.