Kaisen Yang

Student Researcher at Tsinghua University. | yks23@mails.tsinghua.edu.cn

kaisen.jpg

(+86)15019000811

Beijing, China

🧑‍🎓 Biography

I am a third-year undergraduate student in the Department of Computer Science and Technology at Tsinghua University(THU) 🚢. I maintain an academic record with a GPA of $\text{3.94/4.0}$, ranking $\text{12th}$ out of $\text{173}$ students. 📊

Currently, I am conducting research as a student researcher in Professor Alex Lamb’s lab, focusing on the critical and evolving field of LLM Reasoning 💡. My research interests center on techniques to enhance the performance and accessibility of Generative Models, especially the following listed fields:

  • Diffusion Model Compression and Quantization
  • Structured LLM Reasoning
  • Masked Diffusion Model
  • Attention Mechanism

I am passionate about exploring methods to build powerful yet resource-conscious AI systems that push the boundaries of computational efficiency. ⚡

🏢 Affiliations

  • Vice chairman of Students’ Association of Science and Technology in CST.
  • Member of 19th Spark Program.

news

Feb 15, 2026 🎉 Our paper, PAM, has been accepted to CVPR 2026!
Feb 01, 2026 ✍️ 1 preprint released on arXiv.
Jan 20, 2026 🎉 Our paper, CubeBench, has been accepted to ICLR 2026!
Dec 15, 2025 ✍️ 1 preprint released on arXiv.
Nov 20, 2025 🎉 Awarded 2025 九井之星 and Ruiqi Scholarship (20000 RMB).
Sep 15, 2025 💰 Receive ¥30,000 RMB in support from the Beijing Natural Science Foundation for my research project.

selected publications

  1. ACL
    tree-kg.png
    Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains
    Songjie Niu†, Kaisen Yang†, Rui Zhao, Yichao Liu, Zonglin Li, and 2 more authors
    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025
  2. NeurIPS
    impromptu-vla.png
    Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
    Haohan Chi, Huan-ang Gao, Ziming Liu, Jianing Liu, Chenyu Liu, and 6 more authors
    arXiv preprint arXiv:2505.23757, 2025
  3. CVPR
    pam.png
    PAM: A Pose–Appearance–Motion Engine for Sim-to-Real HOI Video Generation
    Mingju Gao†, Kaisen Yang†, Huan-ang Gao, Bohan Li, Ao Ding, and 11 more authors
    In , 2026
  4. ICLR
    cubebench.png
    CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations
    Huan-ang Gao, Zikang Zhang, Tianwei Luo, Kaisen Yang, Xinzhe Juan, and 7 more authors
    In , 2026
  5. ArXiv
    masked-diffusion.png
    Improving Sampling for Masked Diffusion Models via Information Gain
    Kaisen Yang, Jayden Teoh, Kaicheng Yang, Yitong Zhang, and Alex Lamb
    2026
    PDF