Anh-Quan Pham

Welcome to my website. Please feel free to read more about me, or you can check out my CV, projects, or contact me.

I am a final-year master's student in Robotics at the GRASP Lab, University of Pennsylvania. I am also currently the President of the Penn Robotics Entrepreneurs Club (PREC).

I enjoy thinking about problems in scalable robot learning and reinforcement learning. I am fortunate to be advised by Professors Dinesh Jayaraman, Eric Eaton, and Kostas Daniilidis, and to collaborate closely with Professors Jorge Méndez‑Méndez, Dani S. Bassett, and Osbert Bastani. I am incredibly grateful to be mentored by Marcel Hussing in reinforcement learning, and by Junyao Shi and Subin Kim in robot learning in my day-to-day research.

Before that, I studied interpretable reinforcement learning at the A*STAR Institute for Infocomm Research Singapore under Dr. Senthilnath Jayavelu. During my 2.5 years of undergrad at VinUniversity, I applied RL to next-generation telecommunication networks under Professor Van‑Dinh Nguyen, exploring resource allocation and network slicing.

Selected Work

§ Equal contribution (unless noted). † Equal advising. ‡ Project lead.

Iterative Compositional Data Generation for Robot Control

Anh-Quan Pham, Marcel Hussing, Shubhankar P. Patankar, Dani S. Bassett, Jorge Mendez‑Mendez, Eric Eaton

Transactions on Machine Learning Research (TMLR), 2026

SummaryWebsiteJournal/PublisherarXivPDFCodeOpenReviewXBluesky

Closing the Asset-to-Simulation Gap for Articulated Objects via Multi-Modal Physical Refinement

Anh-Quan Pham^§, Sagnik Anupam^§, Luyang Hu^§, Kaitian Chao, George Gao, Tianyou Wang, Junyao Shi, Osbert Bastani^†, Dinesh Jayaraman^†

§ Sorted in alphabetical order by last name; modified for clarity.

Under Review

Summary

Zero-Shot In-Context Learning for Vision-Language-Action (VLA) Models

Anh-Quan Pham^§

§ With additional co-first authors (names forthcoming).

Upcoming submission, May 2026

Summary