William Chen

verityw [AT] berkeley [DOT] edu | LinkedIn | GitHub | Twitter

I am a Computer Science PhD candidate at UC Berkeley's RAIL Lab, advised by Dr. Sergey Levine. My research focuses on Robots That Reason.

Previously, I received a M.Eng. in Electrical Engineering and Computer Science from MIT, after having finished my B.S. in the same department. I conducted my thesis work in the SPARK Lab, where I investigated the use of language models to improve robots' abilities to understand their environments under Dr. Luca Carlone and Jacob Andreas.

I was also a robotics intern at NASA's Jet Propulsion Laboratory.

Publications


FRS: Improving Robotic Generalist Policies via Flow Reversal Steering

Andy Tang, William Chen, Andrew Wagenmaker, Chelsea Finn, Sergey Levine
Paper · Website

This work was accepted at CoRL 2026, as well as at RSS 2026's Diffusion for Robot Learning and 3rd Workshop on Semantic Reasoning and Goal Understanding in Robotics workshops, where it won Best Student Paper at both! This work was co-first authored by Andy Tang and me.


Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control

William Chen, Jagdeep Bhatia, Catherine Glossop, Nikhil Mathihalli, Ria Doshi, Andy Tang, Danny Driess, Karl Pertsch, Sergey Levine
Paper · Website · Code

This work was accepted at RSS 2026.


ECoT-Lite: Training Strategies for Efficient Embodied Reasoning

William Chen, Suneel Belkhale, Suvir Mirchandani, Oier Mees, Danny Driess, Karl Pertsch, Sergey Levine
Paper · Website

This work was accepted at CoRL 2025, where it was selected as an Oral Presentation.


ECoT: Robotic Control via Embodied Chain-of-Thought Reasoning

Michał Zawalski, William Chen, Karl Pertsch, Oier Mees, Chelsea Finn, Sergey Levine
Paper · Website · Code · Models · Colab

This work was accepted at CoRL 2024. It was also featured in the 2024 State of AI report (slide 77). This work was co-first authored by Michał Zawalski and me.


PR2L: Vision-Language Models Provide Promptable Representations for Reinforcement Learning

William Chen, Oier Mees, Aviral Kumar, Sergey Levine
Paper · Website

This work was accepted to TMLR March 2025.

Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?

Filippo Lazzati, Kyle Stachowicz, William Chen, Alberto Maria Metelli, Andrew Wagenmaker, Sergey Levine
Paper · Website

This work was accepted at CoRL 2026.


PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies

Arhan Jain, Mingtong Zhang, Kanav Arora, William Chen, Marcel Torne, Muhammad Zubair Irshad, Sergey Zakharov, Yue Wang, Sergey Levine, Chelsea Finn, Wei-Chiu Ma, Dhruv Shah, Abhishek Gupta, Karl Pertsch
Paper · Website

This work was accepted at RSS 2026.


LITEN: Learning Affordances at Inference-Time for Vision-Language-Action Models

Ameesh Shah, William Chen, Adwait Godbole, Federico Mora, Sanjit A. Seshia, Sergey Levine
Paper · Website

This work was accepted at ICRA 2026.


Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies

Jared Strader, Nathan Hughes, William Chen, Alberto Speranzon, Luca Carlone
Paper


LaMPP: Language Models as Probabilistic Priors for Perception and Action

Belinda Z. Li, William Chen, Pratyusha Sharma, Jacob Andreas
Paper


Organizing and Service

Workshops

Talks


Education

University of California, Berkeley

Ph.D. - Computer Science (June 2023 - Present)
Supported by the NDSEG Fellowship.
Teaching Assistant for Deep Learning (Fall 2024).

Massachusetts Institute of Technology

M.Eng. - Electrical Engineering and Computer Science (Feb 2022 - June 2023)
Teaching Assistant for Natural Language Processing (Fall 2022).
Teaching Assistant for Robotics: Science and Systems (Spring 2021, 2022).

B.S. - Electrical Engineering and Computer Science (Aug 2019 - Feb 2022)

Bronx High School of Science

High School (Sept 2015 - June 2019)