hongmm [at] uw [dot] edu
I am a visiting researcher at the University of Washington advised by Jesse Zhang and Abhishek Gupta.
Previously, I studied at the University of Southern California (USC) working with Anthony Liang, Jesse Zhang, Erdem Bıyık, Stephen Tu, and Jesse Thomason.
My research interests lie in robot learning, reinforcement learning, and generative modeling. I am particularly interested in enabling robots to adapt to new tasks efficiently through human guidance and autonomously in the real world.
News
Publications
TMRL: Exploration via Diffusion Timestep-Modulated Reinforcement Learning
Matthew Hong,
Jesse Zhang,
Dieter Fox,
Anusha Nagabandi,
Abhishek Gupta
World Modeling Workshop 2026
Coming Soon
HAND Me the Data: Fast Robot Adaptation via Hand Path Retrieval
Matthew Hong,
Anthony Liang*,
Kevin Kim,
Harshita Rajaprakash,
Jesse Thomason†,
Erdem Bıyık†,
Jesse Zhang†
ICRA 2026
RSS 2025 Workshop on Human-in-the-Loop Robot Learning
Paper
•
Webpage
•
Coming Soon
CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
Anthony Liang*,
Pavel Czempin*,
Matthew Hong,
Yutai Zhou,
Erdem Bıyık†,
Stephen Tu†
Under Review
Paper
•
Webpage
•
Coming Soon
Multi-Agent Path Finding via Offline RL and LLM Collaboration
Merve Atasever,
Matthew Hong,
Mihir Nitin Kulkarni,
Qingpei Li,
Jyotirmoy V. Deshmukh
Under Review
Paper