Kaiyan Zhang

PhD Student, Tsinghua University

I am a third-year PhD student at the Department of Electronic Engineering, Tsinghua University, under the guidance of Professor Bowen Zhou. I previously earned a Master’s degree in Computer Science and Technology in 2022 from the Harbin Institute of Technology (HIT), where I was supervised by Weinan Zhang and Ting Liu in the HIT-SCIR lab.

My primary research interests focus on the alignment and collaboration of large language models (LLMs), aiming to develop trustworthy and scalable collaborative intelligence systems. I am particularly interested in knowledge discovery facilitated by LLMs and the integration of System 1 and System 2 cognitive processes.

news

Jan 23, 2025 One first-author paper has accepted to ICLR 2025 (see OpenPRM).
Dec 24, 2024 One paper has accepted to AAAI 2025 (Congrats to Xinwei).
Sep 27, 2024 One first-author paper has accepted to NeurIPS 2024 D&B Track (see UltraMedical).
Sep 20, 2024 One paper has accepted to EMNLP 2024 (see LPA).
Jul 10, 2024 One co-first author paper has accepted to COLM 2024 (see LLM4BioHypoGen).
May 16, 2024 Two papers have accepted to ACL 2024 (One first-author, see CoGenesis).
Mar 13, 2024 One paper has accepted to NAACL 2024 (see PAD).
Oct 06, 2023 One first-author paper has accepted to EMNLP 2023 (see CRaSh).

selected publications

  1. ICLR 2025
    OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees
    Kaiyan Zhang, Jiayuan Zhang, Haoxin Li, Xuekai Zhu, Ermo Hua, Xingtai Lv, Ning Ding, Biqing Qi, and Bowen Zhou
    The Thirteenth International Conference on Learning Representations, 2025
  2. Arxiv
    Towards Building Specialized Generalist AI with System 1 and System 2 Fusion
    Kaiyan Zhang, Biqing Qi, and Bowen Zhou
    Preprint, 2024
  3. Arxiv
    Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
    Kaiyan Zhang, Jianyu Wang, Ning Ding, Biqing Qi, Ermo Hua, Xingtai Lv, and Bowen Zhou
    Preprint, 2024
  4. NeurIPS 2024
    Ultramedical: Building specialized generalists in biomedicine
    Kaiyan Zhang, Sihang Zeng, Ermo Hua, Ning Ding, Zhang-Ren Chen, Zhiyuan Ma, Haoxin Li, Ganqu Cui, Biqing Qi, Xuekai Zhu, and 1 more author
    The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2024
  5. ACL 2024
    CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
    Kaiyan Zhang, Jianyu Wang, Ermo Hua, Biqing Qi, Ning Ding, and Bowen Zhou
    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
  6. COLM 2024
    Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation
    Biqing Qi*Kaiyan Zhang*, Kai Tian, Haoxiang Li, Zhang-Ren Chen, Sihang Zeng, Ermo Hua, Hu Jinfang, and Bowen Zhou
    First Conference on Language Modeling, 2024
  7. EMNLP 2023
    CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model
    Kaiyan Zhang, Ning Ding, Biqing Qi, Xuekai Zhu, Xinwei Long, and Bowen Zhou
    Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023