Yihang Sun

LLM, Graph Learning

YihangSun.jpg

I am a first-year MSCS student at UIUC, fortunate to be advised by Prof. Jiaxuan You. I received my Bachelor’s degree in Computer Science from the School of EECS, Peking University, in 2025.

Currently, my research interests primarily focus on the application of LLMs, with an emphasis on the interaction between humans and LLMs. Key areas of interest include:

  • LLM Personalization. Developing lightweight LLM personalization frameworks that effectively leverage user–LLM interaction data to better infer and align with user preferences.

  • Enhancing LLMs with Graphs. Graphs can formalize entities with interconnected relationships, making them well-suited to enhance LLMs, which handle vast amounts of common knowledge and tackle complex semantic tasks.

  • Beyond the above, I am also interested in exploring various directions within the empirical aspects of evaluating and improving the interpretability, fairness, privacy, robustness, and reasoning capabilities of LLMs, ultimately advancing their benefits to humanity.

Feel free (and please do!) to reach out if you have any questions, comments about my research, or anything you’d like to discuss or share with me!

news

Nov 04, 2025 We have open-sourced the code for GMTRouter! 🚀
Check it out here: https://github.com/ulab-uiuc/GMTRouter The preprint will be released on arXiv soon — stay tuned! 📄✨
Aug 19, 2025 I am excited to embark on a new journey as I officially start my MSCS degree at UIUC! 🎓✨ I will be working under the guidance of Prof. Jiaxuan You. This marks a fresh beginning and a thrilling chapter in my academic life! 🌟🚀
Jul 04, 2025 I am thrilled to share that I have officially graduated from Peking University with a Bachelor’s degree in Information and Computational Science! 🎉 A huge thank you to my alma mater and all my friends over the past four years for your support and encouragement! 🙏💡
Jan 23, 2025 Excited to share that GraphEval has been accepted at ICLR 2025! 🎉 Check out the project page here: GraphEval Project 🔗

selected publications

  1. ICLR 2025
    GraphEval.png
    GraphEval: A Lightweight Graph-based LLM Framework for Idea Evaluation
    Tao Feng*, Yihang Sun*, and Jiaxuan You
    2025
  2. AAAI 2024
    ProAgent.png
    Proagent: Building Proactive Cooperative Agents with Large Language Models
    Ceyao Zhang*, Kaijie Yang*, Siyi Hu*, and 8 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2024
  3. Preprint
    PREMIUM.png
    PREMIUM: LLM Personalization with Individual-level Preference Feedback
    Yihang Sun, Tao Feng, Ge Liu, and 1 more author
    2025