Will Liang

willjhliang@gmail.com (github, linkedin, gscholar, twitter, notes)

I'm a computer science student at the University of Pennsylvania. My research interests include robot learning, multimodal representations, generative models, and reinforcement learning for capable and robust embodied agents. At Penn, I'm part of the GRASP Laboratory, where I'm fortunate to work with Jason Ma, Dinesh Jayaraman, and Osbert Bastani.

Previously, I've interned at Microsoft (Fungible), Anduril Industries, and Hudson River Trading, working on live sensor data and machine learning infrastructure. I've also dabbled in traditional art and game development.

I am looking for Fall 2025 PhD opportunities!

Updates

Nov 2024: Trained parkour skills via an adaptive and automatic environment curriculum—Eurekaverse!
May 2024: Globe-walked our dog around campus, trained with LLM-powered sim-to-real—DrEureka.
Oct 2023: Taught a robot hand some pen spinning tricks with evolutionary reward design—Eureka!
Aug 2023: Met awesome people at CMMRS, hosted by MPI-SWS, Cornell, and University of Maryland.
May 2023: Conducted real robot experiments for multimodal representations—LIV.
Aug 2021: Started school at Penn.
Aug 2020: Played Snake with evolutionary algorithms and tensor decomposition, mentored by Ryan Solgi.

Research

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)

(paper, website, code)

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)
ICRA Workshop on Agile Robotics, 2024 (Oral)
ICRA MyoSymposium Workshop, 2024
CVPR Embodied AI Workshop, 2024

(paper, website, code)

Eureka: Human-Level Reward Design via Coding Large Language Models

Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi "Jim" Fan†, Anima Anandkumar†

International Conference on Learning Representations (ICLR), 2024
CoRL Workshop on Language and Robot Learning, 2023 (Oral)
CoRL Towards Generalist Robotics Workshop, 2023 (Oral)
NeurIPS Agent Learning in Open-Endedness Workshop, 2023 (Oral)
NeurIPS Workshop on Foundation Models for Decision Making, 2023

(paper, website, code)

LIV: Language-Image Representations and Rewards for Robotic Control

Yecheng Jason Ma, William Liang, Vaidehi Som, Vikash Kumar, Amy Zhang, Osbert Bastani, Dinesh Jayaraman

arXiv, 2023 (extended ICML version)
RSS Workshop on Utilizing Language for Robot Learning, 2023 (Oral)
CoRL Workshop on Language and Robot Learning, 2023

(paper)

Tensor Shape Search for Efficient Compression of Tensorized Data and Neural Networks

Ryan Solgi, Zichang He, William Liang, Zheng Zhang, Hugo A. Loaiciga

Applied Soft Computing, 2023.

(paper)

(* denotes equal contribution, † denotes equal advising)