尚靖桓 Jinghuan Shang

I'm a Ph.D. candidate in the Department of Computer Science at Stony Brook University, working with Prof. Michael Ryoo, as a part of CV Lab at Stony Brook. I received my Bachelor's degree from IEEE Honored Class at Shanghai Jiao Tong University (SJTU) in 2018, with honor from Shanghai.

Research interest: Representation Learning, Robotics, and Computer Vision. Specifically, I find good visual representations for robots to perform visual tasks under reinforcement learning and imitation learning settings.

[CV][GitHub][Notes(*new!)] Email: jishang [at] cs &dot& stony brook %dot% edu

News

2023/09 - Paper on Active RL is accepted to NeurIPS 2023.

2023/07 - Crossway Diffusion for Diffusion-based Imitation Learning.

2023/06 - Introducing Active Reinforcment Learning under Limited Visual Observability and the library Active-Gym.

2022/09 - 3DTRL and Study on SSL+RL are accepted to NeurIPS 2022.

2022/09 - TRITON for robot sim2real is accepted to CoRL 2022.

2022/09 - StARformer for real robot is accepted to TPAMI. A cute ground mobility robot is able to continuously follow me purely by visual inputs.

2022/08 - Started a research internship at Motional.

2022/07 - StARformer is accepted to ECCV 2022. Local representations benefit long-term sequence modeling in Decision Transformer.

Publications and Preprints

Active Reinforcement Learning under Limited Visual Observability
Jinghuan Shang and Michael S. Ryoo
NeurIPS 2023
[Project Page] [Code] [Env] [arXiv]
Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning
Xiang Li, Varun Belagali, Jinghuan Shang and Michael S. Ryoo
Arxiv Pre-print 2023
[arXiv]
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
Jinghuan Shang, Srijan Das, and Michael S. Ryoo
NeurIPS 2022
[Project Page] [Code] [arXiv]
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
Xiang Li, Jinghuan Shang, Srijan Das, and Michael S. Ryoo
NeurIPS 2022
[arXiv]
Neural Neural Textures Make Sim2Real Consistent
Ryan Burgert, Jinghuan Shang, Xiang Li, and Michael S. Ryoo
CoRL 2022
[Project Page] [Code] [arXiv]
StARformer: Transformer with State-Action-Reward Representations for Robot Learning
Jinghuan Shang, Xiang Li, Kumara Kahatapitiya, Yu-Cheol Lee, Michael S. Ryoo
IEEE TPAMI, Special Issue on Transformer Models in Vision, 2022
[PDF] [IEEE Xplore] [Code]
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
Jinghuan Shang, Kumara Kahatapitiya, Xiang Li, and Michael S. Ryoo
ECCV 2022
[arXiv] [Code] [Video] [Poster]
Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning
Jinghuan Shang and Michael S. Ryoo
IROS 2021
[arXiv] [Talk] [Digest Slide]

Honors and Awards

2022/10- NeurIPS 2022 Scholar Award
2018/08- Merit Scholarship from the Department of Computer Science at Stony Brook University
2018/06- Outstanding graduate among all graduates from universities in Shanghai
2016- 1st Prize in Shanghai Division of China Undergraduate Mathematical Contest in Modeling (CUMCM)
2015-2017- 3 times of Academic Excellence Scholarship at Shanghai Jiao Tong University

Fun

I love cooking.

I solve some algorithm problems in my spare time. Luckily got Top 10 in 2020 SBU ICPC Slection Contest. Here is my [Leetcode].

Last modified 2022/09. Style Credit: latex.css