Jiahui Zhang

I'm a research intern at Horizon Robotics, working with Haonan Yu and Wei Xu. Before at Horizon Robotics, I was a research student at Cognitive Learning for Vision and Robotics Lab (CLVR), advised by Prof. Joseph J. Lim.

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.

Twitter  /  Linkedin  /  CV

profile photo

Email: jzhang96@usc.edu

SPRINT: Scalable Semantic Policy Pretraining via Language Instruction Relabeling
Jesse Zhang*, Karl Pertsch*, Jiahui Zhang, Taewook Nam, Sung Ju Hwang, Xiang Ren, Joseph Lim
Neural Information Processing Systems (NeurIPS) 2022, DeepRL Workshop
Conference on Robot Learning (CoRL) 2022, LangRob Workshop (Spotlight)

We propose a language-guided offline reinforcement pre-training for long-horizon skills.

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