Jiahui Zhang

I'm a research associate at General Robotics Lab, Duke University, under the supervision of Prof. Boyuan Chen.

Before at Duke University, I spent two years as a research student at Cognitive Learning for Vision and Robotics Lab (CLVR), advised by Prof. Joseph J. Lim. I also interned at Horizon Robotics, working with Haonan Yu and Wei Xu.

I received my master's degree in Electronic Engineering from University of Southern California (USC). Before that, I did my undergraduate in Fan Gongxiu Honors College at the Beijing University of Technology and majored in Electronic Information Engineering.

My research interests lie in reinforcement learning and robotics. I am interested in offline RL, skill learning and the intersection of RL and vision.

Google Scholar  /  Twitter  /  Linkedin  /  CV


I am actively seeking a Ph.D. position for Fall 2024.

profile photo
Publications
Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance
Jesse Zhang, Jiahui Zhang, Karl Pertsch, Ziyi Liu, Xiang Ren, Minsuk Chang, Shao-Hua Sun, Joseph J. Lim
CoRL 2023 (Oral)
[OpenReview]

We propose BOSS, an approach that automatically learns to solve new long-horizon, complex, and meaningful tasks by growing a learned skill library with minimal supervision.



SPRINT: Scalable Semantic Policy Pretraining via Language Instruction Relabeling
Jesse Zhang, Karl Pertsch, Jiahui Zhang, Joseph J. Lim
In Submission
[Arxiv] [Website] [Code]

We propose SPRINT, a scalable approach for pre-training robot policies with a rich repertoire of skills while minimizing human annotation effort. Given a dataset of robot trajectories with an initial set of task instructions for offline pre-training, SPRINT expands the pre-training task set without additional human effort via language-model-based instruction relabeling and cross-trajectory skill chaining.




Projects


Cross Domain Imitation Learning Through MPC

Jiahui Zhang, Haonan Yu, Jesse Zhang, Joseph J. Lim, Wei Xu

We present a novel approach leveraging source trajectory and target state-action similarity to replicate the task in the source domain.

Award
    Principle’s scholarship, Beijing University of Technology. 2018
    Outstanding Research Achievement Award, Beijing University of Technology, Fan Gongxiu Honors College. 2017

Template borrow from Jon Barron's website