Hi👋 I am Xiao Bang, an undergrad student major in Computer Science in Shanghai Jiao Tong University, supervised by Cewu Lu and Yonglu Li. I am also selected as a member of Zhiyuan Honors Program.
Currently, I am working on Human Object Interaction (HOI) and Human Motion Generation. Besides, I also have a strong interest in representation learning, self-supervised learning, and 4D.
My long-term goal is to build intelligent systems that can perceive, reason about, and interact with the outside world.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Shanghai Jiao Tong UniversityB.S. in Computer Science, Zhiyuan Honors ProgramSep. 2023 - now -
No.1 Middle School Affiliated to Central China Normal UniversityHigh SchoolSep. 2020 - Jun. 2023
Experience
-
SJTU MVIG Lab
Superviser: Cewu Lu and Yonglu LiResearch InternDec. 2024 - Now -
SJTU EPIC Lab
Superviser: Linfeng ZhangResearch InternAug. 2024 - Dec. 2024
Publications (view all )
Token Pruning for Caching Better: 9$\times$ Acceleration on Stable Diffusion without Training
Evelyn Zhang*, Bang Xiao*, Fufu Yu, Jiayi Tang, Chang Zou, Ke Yan, Shouhong Ding, Qianli Ma, Fei Ren, Linfeng Zhang# (* equal contribution, # corresponding author)
Submitted to ICCV 2025
Based on token prune and layer cache technology, we present a new Stable Diffusion acceleration method named dynamics-aware token pruning (DaTo). In the COCO-30k, we observed a 7$\times$ acceleration coupled with a notable FID reduction of 2.17.
Token Pruning for Caching Better: 9$\times$ Acceleration on Stable Diffusion without Training
Evelyn Zhang*, Bang Xiao*, Fufu Yu, Jiayi Tang, Chang Zou, Ke Yan, Shouhong Ding, Qianli Ma, Fei Ren, Linfeng Zhang# (* equal contribution, # corresponding author)
Submitted to ICCV 2025
Based on token prune and layer cache technology, we present a new Stable Diffusion acceleration method named dynamics-aware token pruning (DaTo). In the COCO-30k, we observed a 7$\times$ acceleration coupled with a notable FID reduction of 2.17.