Biography

I am Kaicheng Yang (杨凯程, kaichengyang), an undergraduate researcher at Shanghai Jiao Tong University (SJTU, 上海交通大学). I am also an incoming PhD student at SphereLab, The Chinese University of Hong Kong, where I will work with Prof. Weiyang Liu (刘威杨). My previous work was with Prof. Yulun Zhang (张宇伦).

My research explores the transfer, connection, and carriers of intelligence. I study model quantization as a way to understand how intelligence can be represented in discrete systems, and I am interested in future interfaces that connect machine intelligence with human intelligence.

Research Affiliations

  • SphereLab, The Chinese University of Hong Kong

    Incoming PhD Student · advised by Prof. Weiyang Liu (刘威杨).

    2026.08 – present

  • GenSI Group, Institute for AI Industry Research, Tsinghua University

    Research Intern · discrete diffusion language models, protein foundation models, and model architecture exploration.

    2026.02 – 2026.07

  • Yulun Zhang's Group, Shanghai Jiao Tong University

    Previous work with Prof. Yulun Zhang (张宇伦) · training-aware quantization, post-training quantization, and diffusion models under 1–4 bit precision; supported by NSFC undergraduate research funding.

    2024.09 – 2026.01

Research

My current work begins with discretizing intelligence: identifying which structures survive when continuous models are represented with very few bits. I am interested in where this perspective leads next, including the bandwidth and interfaces between biological and machine intelligence.

News

Sep 2026 We released JustQuant.
Aug 2026 Joined SphereLab at The Chinese University of Hong Kong as an incoming PhD student, working with Prof. Weiyang Liu.
May 2026 RobuQ, Info-Gain, and Q-DiT4SR accepted to ICML 2026.
Feb 2026 Three preprints released on arXiv.
Jan 2026 PT^2-LLM accepted to ICLR 2026.
Oct 2025 National Challenge Cup Grand Prize.
Sep 2025 Three preprints released on arXiv.
Sep 2025 NSFC undergraduate research project support.
May 2025 BiMaCoSR accepted to ICML 2025.

Selected Publications

* indicates equal contribution.

  1. arXiv
    JustQuant: You Don’t Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization
    Kaicheng Yang*, Kaisen Yang*, Chunyu Liu*, Xianglong Yan, Haotong Qin, and 6 more authors
    arXiv preprint arXiv:2609.33601, 2026
    arXiv PDF Blog Website
  2. NeurIPS
    MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
    In NeurIPS (Oral), 2026
    arXiv PDF Website
  3. ICML
    RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
    Kaicheng Yang*, Xun Zhang*, Haotong Qin, Yucheng Lin, Kaisen Yang, and 1 more author
    In International Conference on Machine Learning, 2026
    arXiv PDF Code
  4. ICML
    Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
    Xun Zhang*, Kaicheng Yang*, Hongliang Lu, Haotong Qin, Yong Guo, and 1 more author
    In International Conference on Machine Learning, 2026
    arXiv PDF Code
  5. ICML
    Improving Sampling for Masked Diffusion Models via Information Gain
    Kaisen Yang, Jayden Teoh, Kaicheng Yang, Yitong Zhang, and Alex Lamb
    In International Conference on Machine Learning, 2026
    arXiv PDF Code
  6. ICLR
    PT^2-LLM: Post-Training Ternarization for Large Language Models
    Xianglong Yan*, Chengzhu Bao*, Zhiteng Li, Tianao Zhang, Kaicheng Yang, and 4 more authors
    In International Conference on Learning Representations, 2026
    arXiv PDF Code
  7. ICML
    BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
    Kai Liu*, Kaicheng Yang*, Zheng Chen, Zhiteng Li, Yong Guo, and 3 more authors
    In International Conference on Machine Learning, 2025
    arXiv PDF Code
  8. arXiv
    TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search
    Kaicheng Yang, Kaisen Yang, Baiting Wu, Xun Zhang, Qianrui Yang, and 3 more authors
    arXiv preprint arXiv:2512.06353, 2025
    arXiv PDF Code

Honors

  • 2025 National Challenge Cup Grand Prize
  • 2025 NSFC Undergraduate Research Project Support
  • 2024 Infineon Scholarship
  • 2024 University Second-Class Scholarship
  • 2023 First Prize, National College Student Mathematics Competition