Ruiqi Wang

Hello!

I am a Postdoctoral Research Fellow at the University of Southern California, working with Professor Erdem Bıyık in the Lira Lab. I received my Ph.D. from Purdue University, where I worked with Professor Byung-Cheol Min in the SMART Lab.

My research focuses on robot learning from humans to close the last mile of robot intelligence. Foundation models are giving robots increasingly general capabilities, yet every deployment in the human world ends with a last mile that pretraining cannot cover: a new task the robot has never seen, or a new user with their own preferences. Both are forms of human intent, hard to specify yet easy for people to judge, and closing this gap requires learning from the people who hold it.

Toward this, I develop methods that make every bit of human feedback go further: amplifying scarce feedback with foundation models, capturing human intent in reward structures that are reusable across tasks and users, and enabling robots to infer intent in context from rich multimodal feedback without retraining, so that each new task or person takes fewer steps than the last.

Research Areas:

News