Kai WU

Researcher at ByteDance

prof_pic.jpg

I am a researcher at ByteDance, where my work centers on LLM coding agents — building models and systems that can read, reason about, and write code autonomously.

I received my M.S. from the University of Wisconsin–Madison, where I was fortunate to be advised by Prof. Leyuan Shi and Prof. Xin Wang. 🚀 I am also a Kaggle Master, ranked in the global top 0.2%.

Feel free to reach out — I am always happy to connect.

news

Aug 30, 2026 Our survey AI4AI: From Long-Horizon Agents to Recursive Self-Improvement is online — definitions, reliable horizons, and open problems
Aug 26, 2026 We released AI4AI Awesome-AI4AI — Weekly-updated papers, news, and resources for AI-for-AI research [code]
Feb 15, 2026 We released the Seed 2.0 Model Card — Towards Intelligence Frontier for Real-World Complexity
Feb 13, 2026 We published the MedXIAOHE Tech Report - A Comprehensive Recipe for Building Medical MLLMs
Jan 15, 2026 Two papers accepted by ICLR 2026!

Selected Publications

  1. Seed
    seed20.jpg
    Seed 2.0 Model Card
    ByteDance Seed
    ByteDance Seed Technical Report, 2026
    Link
  2. arXiv
    seed18.png
    Seed1.8 Model Card: Towards Generalized Real-World Agency
    ByteDance Seed
    arXiv preprint arXiv:2603.20633, 2025
    Link
  3. arXiv
    medxiaohe.png
    MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
    Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang, and 14 more authors
    arXiv preprint arXiv:2602.12705, 2025
    Link
  4. NeurIPS
    basereward.png
    BaseReward: A Strong Baseline for Multimodal Reward Model
    Yi-Fan Zhang, Haihua Yang, Huanyu Zhang, Yang Shi, Zezhou Chen, Haochen Tian, and 8 more authors
    In Advances in Neural Information Processing Systems, 2025
    Link
  5. CVPR
    custany.png
    CustAny: Customizing Anything from A Single Example
    Lingjie Kong, Kai Wu, Chengming Xu, Xiaobin Hu, Wenhui Han, Jinlong Peng, and 5 more authors
    In CVPR, 2025
    Oral Link
  6. VI
    efficient_mllm.png
    Efficient Multimodal Large Language Models: A Survey
    Yizhang Jin, Jian Li, Tianyun Gu, Yexin Liu, Bo Zhao, Jinyuan Lai, and 6 more authors
    Visual Intelligence, 2025
    Link
  7. CVPR
    vton_handfit.png
    VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding
    Yujie Liang, Xiaobin Hu, Boyuan Jiang, Donghao Luo, Xiang Peng, Kai Wu, and 5 more authors
    In CVPR, 2025
    Link
  8. ECCV
    tuning_free.png
    Tuning-Free Image Customization with Image and Text Guidance
    Pengzhi Li, Qiang Nie, Ying Chen, Xi Jiang, Kai Wu, Yuhuan Lin, and 4 more authors
    In European Conference on Computer Vision, 2024
    Link
  9. arXiv
    noiseboost.png
    NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
    Kai Wu, Boyuan Jiang, Zhengkai Jiang, Qingdong He, Donghao Luo, Shengzhi Wang, and 2 more authors
    arXiv preprint arXiv:2405.20081, 2024
    Link
  10. AAAI
    ucad.png
    Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt
    Jiaqi Liu, Kai Wu, Qiang Nie, Ying Chen, Bin-Bin Gao, Yong Liu, and 3 more authors
    In AAAI Conference on Artificial Intelligence, 2024
    Link
  11. NeurIPS
    softpatch.png
    SoftPatch: Unsupervised Anomaly Detection with Noisy Data
    Xi Jiang, Jiaqi Liu, Jinbao Wang, Qiang Nie, Kai Wu, Yong Liu, and 2 more authors
    In Advances in Neural Information Processing Systems, 2022
    Link
  12. CVPR
    classaware.png
    Class-Aware Contrastive Semi-Supervised Learning
    Fan Yang, Kai Wu, Shuyi Zhang, Guannan Jiang, Yong Liu, Feng Zheng, and 3 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
    Link