Wenye Lin

Ph.D. Student at The University of Hong Kong (HKU).

prof_pic.jpg

linius@connect.hku.hk

I am currently a third-year Ph.D. student at the Data Science Academy, The University of Hong Kong (HKU), advised by Prof. Kai Han. Prior to this, I received my Master’s degree in Computer Technology from Tsinghua University in 2023, advised by Prof. Hai-tao Zheng, and my Bachelor’s degree in Software Engineering from Nanjing University in 2019.

My research interests primarily lie in Large Language Models (LLMs), Reasoning, and Post-Training. I am particularly focused on enhancing the logical reasoning capabilities of large models on complex tasks, as well as continual learning during post-training.


🎓 Education

  • The University of Hong Kong (HKU), Sep. 2023 - Present
    • Ph.D. in Artificial Intelligence, Data Science Academy
  • Tsinghua University, Aug. 2020 - Jul. 2023
    • M.S. in Computer Technology, Shenzhen International Graduate School
  • Nanjing University, Sep. 2015 - Jun. 2019
    • B.S. in Software Engineering

💻 Experience

  • Tencent AI Lab, NLP Group Sep. 2021 - Aug. 2022
    • Research Intern (Mentor: Lemao Liu)
  • Teaching Assistant
    • Advanced Statistical Modeling (2024 - 2025)
    • Natural Language Processing (2023 - 2026)

news

Jan 15, 2016 A simple inline announcement with Markdown emoji! :sparkles: :smile:
Nov 07, 2015 A long announcement with details
Oct 22, 2015 A simple inline announcement.

latest posts

selected publications

  1. ArXiv
    Surgical Post-Training: Cutting Errors, Keeping Knowledge
    Wenye Lin and Kai Han
    ArXiv preprint, 2026
  2. ACL
    GAMEBoT: Transparent Assessment of LLM Reasoning in Games
    Wenye Lin, Jonathan Roberts, Yunhan Yang, and 3 more authors
    In Annual Meeting of the Association for Computational Linguistics (ACL) main, 2025
  3. ArXiv
    Zerobench: An impossible visual benchmark for contemporary large multimodal models
    J Roberts, M R Taesiri, A Sharma, and 16 more authors
    ArXiv preprint, 2025