XIANG LI
I'm a Ph.D. candidate in the Department of Computer Science at Stony Brook University, working with Prof. Michael S. Ryoo. My research interest includes visual representation learning, robotics and computer vision.
Prior to this, I worked with Prof. Yue Zhou as a
master student and I received my MS and BS from Shanghai Jiao Tong University.
Email: xiangli8 \at cs \dot stonybrook \dot edu
Publication
-
Peekaboo: Text to Image Diffusion Models are Zero-Shot SegmentorsPaper, Code(coming soon)preprint, 2022 -
Neural Neural Textures Make Sim2Real ConsistentCoRL, 2022 -
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?NeurIPS, 2022 -
StARformer: Transformer with State-Action-Reward Representations for Robot LearningIEEE TPAMI, Special Issue on Transformer Models in Vision, 2022 -
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement LearningECCV, 2022
Projects
-
LiDAR based SLAM + GPS + NavigationROS C++ Python
This work was done during my internship at Beijing Falcon Self-driving Co., Ltd.. -
RC Car + Raspi + CameraArduino C++ Python
An open-source solution to transform general RC cars into powerful mobile vision platforms. -
Visual tracking with a moterized cameraC++
Use a moterized camera and STC to track moving vehicles. The moterized cradle was controlled by a PI controller via PELCO-D. GUI was made with MFC. -
I also worked on other projects like playing Android/PC games autonomously using computer vision tricks, GPU cluster monitor based on Grafana and InfluxDB, RTMP streaming, and many Raspberry Pi projects with various sensors. They might not be very challenging but they significantly improved the quality of my life :)
Awards
- Outstanding graduates in Shanghai, 2018
- National scholarship for graduate students, 2017
- Outstanding graduates of SJTU, 2015
Last modified: Nov 23, 2022 | Back to top