Xueyi Chen

Incoming PhD Student @ Westlake · Fall 2026

pic.png

悟已往之不谏

知来者之可追

Hangzhou, Zhejiang, China

About Me

I am Xueyi Chen, an incoming PhD student at Westlake University starting in Fall 2026 advised by Prof. Huan Wang, and currently a research intern at the ENCODE Lab. Previously, I earned my MSc in Computer Science from The Chinese University of Hong Kong (CUHK) in 2025 supervised by Prof. Bei Yu and my BEng in Software Engineering from Fuzhou University in 2024.

Research Interests

I am broadly interested in building efficient and capable AI systems:

I am actively seeking research internships and always open to potential collaborations. Please feel free to contact me at [email protected] or [email protected].

News

Feb 21, 2026 🎉 StreamingTOM has been accepted to CVPR 2026! This is my first top-venue first-author paper! Thanks to all co-authors! See you in Denver!
Special thanks to PTE. for the figure design advice and encouragement during that time!
Oct 21, 2025 📄 Our paper “StreamingTOM: Streaming Token Compression for Efficient Video Understanding” is on arXiv! Thanks to co-authors Keda Tao, Kele Shao, and Prof. Huan Wang. Check it out here!
Oct 15, 2025 🎓 Graduated with my M.Sc. in CS from CUHK! Huge thanks to my advisor Prof. Bei Yu and collaborators Rui Ming and Haoyuan Wu. Next stop: Westlake University!
Oct 01, 2025 🎉 Thrilled to receive a Ph.D. offer from Prof. Huan Wang at Westlake University! Excited to continue working with the amazing team at ENCODE Lab!
Jun 30, 2025 🚀 Joined ENCODE Lab at Westlake University as a visiting student, advised by Prof. Huan Wang. Excited to work on efficient AI systems!

Selected Publications

  1. StreamingTOM: Streaming Token Compression for Efficient Video Understanding
    Xueyi Chen, Keda Tao, Kele Shao, and Huan Wang
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  2. DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels
    Haolei Bai, Lingcheng Kong, Xueyi Chen, Jianmian Wang, Zhiqiang Tao, and Huan Wang
    arXiv preprint arXiv:2602.11715, Feb 2026
    Under review
  3. On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
    Haoyuan Wu*, Rui Ming*, Jilong Gao*, Hangyu Zhao, Xueyi Chen, Yikai Yang, Haisheng Zheng, Zhuolun He, and Bei Yu
    In Advances in Neural Information Processing Systems (NeurIPS), Sep 2025
  4. ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving
    Haoyuan Wu*, Xueyi Chen*, Rui Ming, Jilong Gao, Shoubo Hu, Zhuolun He, and Bei Yu
    arXiv preprint arXiv:2505.12717, May 2025
    Under review