Kun-Peng Ning   宁鲲鹏

PhD student

Peking University (PKU),

Email: ningkp@stu.pku.edu.cn

Kun-Peng Ning

Biography

I am a second year Ph.D. student in the School of Computer Science at Peking University, advised by Prof. Li Yuan. I received my B.E. and M.S. degrees in computer science from Nanjing University of Aeronautics and Astronautics in 2019 and 2022, respectively, advised by Prof. Sheng-Jun Huang. Moreover, I was a researcher in Tencent AI & ARC Lab and JD Business Growth BU for a year respectively. My research interests include machine learning and large language models.
Welcome to try our ChatExcel!

News

  • [Jan 2025] One paper is accepted to ICLR 2025.
  • [Nov 2024] One paper is accepted to COLING 2025.
  • [Jul 2024] One paper is accepted to CIKM 2024.
  • [Jul 2024] One paper is accepted to ECCV 2024.
  • [Mar 2023] One paper is accepted to ICLR Workshop 2023.
  • [Feb 2023] We have released ChatExcel: An Auto AI Tool for Excel.
  • [Mar 2022] One paper is accepted to CVPR 2022.
  • [Apr 2021] One paper is accepted to IJCAI 2021.
  • [Nov 2020] One paper is accepted to AAAI 2021.
  • [Apr 2019] One paper is accepted to KDD 2019.

    • Publications

    Conference Papers

    PiCO: Peer Review in LLMs based on the Consistency Optimization.

    Kun-Peng Ning, Shuo Yang, Yu-Yang Liu†, Jia-Yu Yao, Zhen-Hui Liu, Yong-Hong Tian, Yi-Bing Song, Li Yuan†.

    The Thirteenth International Conference on Learning Representations ( ICLR ), 2025.

    [PDF][Code]
    Is Parameter Collision Hindering Continual Learning in LLMs?

    Shuo Yang*, Kun-Peng Ning*, Yu-Yang Liu†, Jia-Yu Yao, Yong-Hong Tian, Yi-Bing Song, Li Yuan†

    The 31st International Conference on Computational Linguistics ( COLING ), 2025.

    [PDF][Code]
    Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search.

    Kun-Peng Ning, Ming Pang†, Zheng Fang, Xue Jiang, Xi-Wei Zhao, Zhan-Gang Lin, Li Yuan†

    ACM Conference on Information and Knowledge Management ( CIKM ), 2024.

    [PDF]
    Bidirectional Uncertainty-Based Active Learning for Open Set Annotation.

    Chen-Chen Zong, Ye-Wen Wang, Kun-Peng Ning, Hai-Bo Ye, Sheng-Jun Huang†

    European Conference on Computer Vision ( ECCV ), 2024.

    [PDF][Code]
    Co-Imitation Learning without Expert Demonstration.

    Kun-Peng Ning, Hu Xu, Kun Zhu, Sheng-Jun Huang†.

    ( ICLR Workshop ), 2023.

    [PDF]
    Active Learning for Open-set Annotation.

    Kun-Peng Ning, Xun Zhao†, Yu Li, Sheng-Jun Huang†.

    IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2022.

    [PDF][Code]
    Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries.

    Kun-Peng Ning, Lue Tao, Songcan Chen, Sheng-Jun Huang†.

    The 35th Association for the Advancement of Artifificial Intelligence ( AAAI ), 2021.

    [PDF]
    Asynchronous Active Learning with Distributed Label Querying.

    Sheng-Jun Huang†, Chen-Chen Zong, Kun-Peng Ning, Hai-Bo Ye.

    The 30th International Joint Conference on Artificial Intelligence ( IJCAI ), 2021.

    [PDF]
    Tackle balancing constraint for incremental semi-supervised support vector learning.

    Shuyang Yu, Bin Gu†, Kun-Peng Ning, Haiyan Chen, Jian Pei, and Heng Huang.

    The 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining ( KDD ), 2019.

    [PDF]

    Preprints

    GPT as a Monte Carlo Language Tree: A Probabilistic Perspective.

    Kun-Peng Ning, Jia-Yu Yao, Yu-Yang Liu, Mu-Nan Ning, Li Yuan†.

    arXiv preprint arXiv: 2501.07641, 2025.

    [PDF][Code]
    LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples.

    Jia-Yu Yao*, Kun-Peng Ning*, Zhen-Hui Liu*, Mu-Nan Ning, Li Yuan†.

    arXiv preprint arXiv: 2310.01469, 2023.

    [PDF][Code]

    Professional Services

  • Conference Program Committee Member/Reviewer: CVPR'23,24,25, NIPS'24,25, ICLR'25, ICML'25, ICCV'25, AISTATS'25
  • Journal Reviewer: IEEE TNNLS

    • Experiences

  • Algorithm Engineer | JD Business Growth BU, Beijing, China | June 2022 - June 2023
  • Research Intern | Tencent ARC Lab, Shenzhen, China | June 2021 - December 2021
  • Research Intern | Tencent AI Lab, Shenzhen, China | August 2020 - February 2021