Yuxuan Li 李宇轩

Hi there! I recently graduated with a Master's degree in Electrical Engineering from Northwestern University, where I was advised by Prof. Stephen Xia. I am currently a Research Assistant at the University of Southern California, working with Prof. Daniel Seita. Previously, I received my Bachelor's degree from the University of Science and Technology Beijing.

My research interests generally focus on robot learning and reinforcement learning. Recently, I am particularly interested in (1) efficient and generalizable robot learning from limited data, and (2) understanding and improving Vision-Language-Action (VLA) models for human preferences through interpretability. My goal is to enable robots to learn efficiently and behave reliably in diverse real-world scenarios.

Email  /  GitHub  /  Google Scholar  /  Twitter

Publications

TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning

We propose Time-Weighted Contrastive Reward Learning (TW-CRL), an Inverse Reinforcement Learning framework that leverages both successful and failed demonstrations along with the temporal information within them.

Website Template