Xiaoyang Kang

I am currently a Research Engineer at a video generation startup. Previously, I spent several productive years at Alibaba Group, where I served as a Research Engineer at Alimama Creative Lab, Tongyi Lab, and DAMO Academy. My work primarily focused on pushing the boundaries of generative AI and its industrial applications.

I obtained my M.S. and B.S. degrees in Computer Science and Technology from Beijing University of Posts and Telecommunications (BUPT). My research interests lie in Generative Models, Video Generation, and Enhancement. I am passionate about building next-generation creative tools powered by foundation models.

Email  /  Github  /  Google Scholar

profile photo
Selected Publications
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
SII-GAIR, Sand.ai: Ethan Chern, Hansi Teng, Hanwen Sun, Hao Wang, Hong Pan, Hongyu Jia, ..., Xiaoyang Kang, Yan Ma, Yixiu Liu, Yunbo Zhang, Yunpeng Huang, Yutong Lin, Zewei Tao, Zhaoliang Liu, Zheng Zhang, Zhiyao Cen, Zhixuan Yu, Zhongshu Wang, Zhulin Hu, Zijin Zhou, Zinan Guo, Yue Cao, Pengfei Liu
Authors are listed in alphabetical order.
Technical Report , 2026
paper / code
MAGI-1: Autoregressive Video Generation at Scale
Sand.ai, Hansi Teng, Hongyu Jia, Lei Sun, Lingzhi Li, Maolin Li, Mingqiu Tang, Shuai Han, Tianning Zhang, W.Q. Zhang, Weifeng Luo, Xiaoyang Kang, Yuchen Sun, Yue Cao, Yunpeng Huang, Yutong Lin, Yuxin Fang, Zewei Tao, Zheng Zhang, Zhongshu Wang, Zixun Liu, et al.
Authors are listed in alphabetical order.
Technical Report , 2025
paper / code
AtomoVideo: High Fidelity Image-to-Video Generation
Litong Gong*, Yiran Zhu*, Weijie Li*, Xiaoyang Kang*, Biao Wang, Tiezheng Ge, Bo Zheng
* co-first authors
Technical Report , 2024
paper / project
DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders
Xiaoyang Kang, Tao Yang, Wenqi Ouyang, Peiran Ren, Lingzhi Li, Xuansong Xie
ICCV , 2023
paper / code / demo
RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters
Wenqi Ouyang, Yi Dong, Xiaoyang Kang, Peiran Ren, Xin Xu, Xuansong Xie
ICCV , 2023
paper / code
NTIRE 2023 Video Colorization Challenge
Xiaoyang Kang, Xianhui Lin, Kai Zhang, Zheng Hui, Wangmeng Xiang, Jun-Yan He, Xiaoming Li, Peiran Ren, Xuansong Xie, Radu Timofte
CVPRW , 2023
paper / project
Experience
  • 2025.3 - Present:   Research Engineer at Sand.ai, Beijing.
  • 2022.7 - 2025.2:   Research Engineer at Tongyi Lab and Alimama Creative Lab, Alibaba Group, Beijing.
  • 2021.6 - 2022.6:   Algorithm Intern at Alibaba Cloud, Alibaba Group, Beijing.
  • 2021.3 - 2021.6:   Algorithm Intern at Tiktok, ByteDance, Beijing.
  • 2020.7 - 2020.10:   Research Intern at SenseTime AI Lab, Beijing.
Awards and Honors
  • Silver Medal (Top 1.3%), Kaggle Cassava Leaf Disease Classification, 2021
  • Outstanding Graduates of Beijing (Top 5%), 2019
  • First Prize, Innovation and Entrepreneurship Competition of BUPT, 2019
  • Merit Student Award (Top 10%), BUPT, 2017
  • 🏆 Champion, Alibaba Taobao & Tmall Group Beijing Basketball Tournament, 2024

Thanks to Jon Barron for sharing the code of his personal webpage.