Biography

I am an undergraduate at the Department of Computer Science and Technology, Tsinghua University. GPA: 3.9/4.0 · Rank: 8/194.

My research interests span Generative Modeling, Agents, and Physical AI.

Layer 1 · Paradigms

Modeling Paradigms

How can we decompose a complex target into functions that are tractable to model?

Layer 2 · Systems

Architectures & Efficiency

How can we model these functions efficiently and precisely?

Layer 3 · Evidence

Data & Benchmark

How do we learn these functions and evaluate them rigorously?

Research Affiliations

Service & Activities

  • Chairman, Students’ Association of Science and Technology, Department of CST, Tsinghua University.
  • Council Member, 19th Spark Program (星火计划), Tsinghua University.
  • Former Class President, Class 31, Department of CST, Tsinghua University.

News

Sep 25, 2026 Our paper, Frontier-Eng, has been accepted to NeurIPS 2026!
Sep 11, 2026 Awarded RMB 100,000 in undergraduate research funding from the National Natural Science Foundation of China (NSFC).
Aug 31, 2026 Released Safin-1, exploring safety through memory-native state evolution.
Aug 24, 2026 Our paper SWE Refactor Bench evaluates coding agents on whole-repository stack migration.
Aug 20, 2026 Released AI4AI-Bench, a benchmark for algorithmic design and recursive self-improvement.
Aug 12, 2026 Our paper MARCH introduces content-routed state anchors for recurrent memory.

Selected Publications

  1. ArXiv
    safin.png
    Safin-1: Safety from Within through Memory-Native State Evolution
    Ming Zhang, Kaisen Yang, Shu Yu, Ermo Hua, Zhekai Chen, and 13 more authors
    2026
    arXiv PDF
  2. ArXiv
    swe-refactor.png
    SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
    Deyao Hong, Yizhe Chi, Wenyi Li, Xiaoqiu Wang, Mingju Gao, Kaisen Yang, and 4 more authors
    2026
    arXiv PDF
  3. ArXiv
    browserbc.png
    Scalable Behaviour Cloning on Browser Using via Skill Distillation
    Kaisen Yang, Zheng Jiang, Yuzhao Peng, Houde Qian, Boshi Zhang, and 9 more authors
    2026
    arXiv HTML PDF
  4. ArXiv
    ai4ai-bench.png
    AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement
    Yizhe Chi, Wenyi Li, Deyao Hong, Xiaoqiu Wang, Mingju Gao, Kaisen Yang, and 4 more authors
    2026
    arXiv HTML PDF Code
  5. COLM
    voidpadding.png
    VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Termination
    Chunyu Liu, Zhengyang Fan, Kaisen Yang, and Alex Lamb
    COLM 2026 Workshop on Efficient Reasoning, 2026
    arXiv PDF Code
  6. NeurIPS
    frontier-eng.png
    Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization
    Dapeng Jiang*, Yizhe Chi*, Kaisen Yang*, Tianwei Luo*, Boshi Zhang*, and 17 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
    * Equal contribution.
    arXiv HTML PDF Code
  7. ICML
    masked-diffusion.png
    Improving Sampling for Masked Diffusion Models via Information Gain
    Kaisen Yang, Jayden Teoh, Kaicheng Yang, Yitong Zhang, and Alex Lamb
    In Proceedings of the 43rd International Conference on Machine Learning, 2026
    arXiv HTML PDF Code
  8. 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 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    arXiv HTML PDF
  9. 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 International Conference on Learning Representations (ICLR), 2026
    arXiv HTML PDF
  10. 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
    HTML PDF
  11. 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, Jinwei Li, Kaisen Yang, and 4 more authors
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    arXiv HTML PDF Code
  12. ICML
    robuq.png
    RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
    Kaicheng Yang†, Xun Zhang†, Haotong Qin, Yucheng Lin, Kaisen Yang, and 2 more authors
    In International Conference on Machine Learning (ICML), 2026
    arXiv PDF Code