Anthony Liang

Ph.D. Student, University of Southern California

I am a rising fourth year Ph.D. student at the University of Southern California coadvised by and Erdem Bıyık (LiRA Lab) and Stephen Tu. I am interested in meta-reinforcement learning (RL) and building generalist agents capable of quickly adapting to new, unseen scenarios. I was a Student Researcher at Google working with Chih-wei Hsu, Yinlam Chow and Guy Tennenholtz on sequential-decision making with dynamic latent contexts. I previously interned at Meta Reality Lab with Paul Crook and Andrea Matto working on task-oriented dialogue systems using LLMs.

Prior to joining USC, I spent a summer (during the pandemic) as a visiting scholar at CMU working with Changliu Liu. I graduated from the University of Michigan with a Masters in Robotics and Bachelors in Computer Science where I worked with Wilka Carvalho and Honglak Lee. I had the pleasure to intern at Amazon, Invisible.ai, Google Ads, Luminar and Socratic.

Feel free to say hi: anthony dot liang at usc dot edu


News

Sept 2024 DynaMITE-RL accepted to NeurIPS 2024 as a poster.
June 2024 PromptDTLA accepted to ICML 2024 ICL Workshop and DynaMITE-RL accepted to AutoRL Workshop
June 2024 ViSaRL accepted to International Conference on Intelligent Robots and Systems (IROS 2024)
May 2023 Student Researcher at Google with the Machine Intelligence group
May 2022 Started at Meta Reality Lab as an NLP Research Intern working on Task-Oriented Dialogue Systems using LLMs
Sept 2021 Started my Ph.D. at USC with the GLAMOR group!
May 2021 Applied Scientist Intern at Amazon
Oct 2020 Preprint out on arXiv: Reinforcement Learning for Sparse-Reward Object-Interaction Tasks

Publications

dynamite-rl

DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning

Anthony Liang, Guy Tennenholtz, Chih-wei Hsu, Yinlam Chow, Erdem Bıyık, Craig Boutilier

AutoRL Workshop at ICML 2024

Accepted to NeurIPS 2024 (25.8% Acceptance Rate)


prompt-dtla

In-Context Generalization to New Tasks From Unlabeled Observation Data

Anthony Liang, Pavel Czempin, Yutai Zhou, Stephen Tu, Erdem Bıyık

1st ICL Workshop at ICML 2024


visarl

ViSaRL: Visual Reinforcement Learning Guided by Human Saliency

Anthony Liang, Jesse Thomason, Erdem Bıyık

Accepted to International Conference on Intelligent Robots and Systems (IROS 2024)

ICRA 2023 Pretraining for Robotics Workshop (PT4R)

Spotlight Talk (Top 15% of submissions)


transformer_adapters

Transformer Adapters for Robot Learning

Anthony Liang, Ishika Singh, Karl Pertsch, Jesse Thomason

CoRL 2022 Workshop on Pretraining for Robot Learning

Spotlight Talk


load

Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in First-person Simulated 3D Environments

Wilka Carvalho, Anthony Liang, Kimin Lee, Sungryull Sohn, Honglak Lee, Richard L. Lewis, Satinder Singh

International Joint Conference on Artificial Intelligence 2021

NeurIPS Deep Reinforcement Learning 2020 Workshop



Teaching

CSCI 699: Robot Learning Fall 2024
CSCI 499: Interactive Natural Language Processing Fall 2023
EECS 442: Computer Vision Winter 2021
EECS 498: Algorithmic Robotics Winter 2020
EECS 504: Graduate Computer Vision Fall 2020
EECS 280: Introduction to Programming and Data Structures Fall 2018, Winter 2018, Fall 2019