👋 Welcome to Chongyu’s home page!

🔹 I am Chongyu Fan (樊翀宇), a first-year Ph.D. student in Computer Science at Michigan State University, supervised by Prof. Sijia Liu. I received B.Eng. from Huazhong University of Science and Technology in 2024.

🔹 Currently, I am a Research Intern at ByteDance, supervised by Dr. Jian Du.

🔹 My research focuses on trustworthy and scalable machine learning, such as machine unlearning.

🔹 Feel free to reach out via email if you’re interested in working together.

🔥 News

2025.05: 🎉 One first-author paper Smooth Unlearn has been accepted in ICML 2025!
2024.10: ✨ One first-author paper SimNPO has been made public on arXiv!
2024.09: 🎉 Two papers UnlearnCanvas and AdvUnlearn have been accepted in NeurIPS 2024!
2024.07: 🎉 One first-author paper Challenging Forgets has been accepted in ECCV 2024!
2024.01: 🎉 One first-author paper SalUn has been accepted in ICLR 2024 as spotlight!

🎯 First-Authored Publications

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Chongyu Fan*, Jinghan Jia*, Yihua Zhang, Anil Ramakrishna, Mingyi Hong, Sijia Liu

ICML 2025

Challenging Forgets: Unveiling the Worst-case Forget Sets in Machine Unlearning

Chongyu Fan*, Jiancheng Liu*, Alfred Hero, Sijia Liu

ECCV 2024

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Dennis Wei, Eric Wong, Sijia Liu

ICLR 2024 Spotlight

📄 CV (Updated: 2025-05-26)

📄

English CV

Here is my CV in English.

📞 Contact

📧

Email

fanchon2@msu.edu

chongyu.fan93@gmail.com

📈 Experience

🎓 Education

  • 2024.09–Present, Ph.D. in CS, Michigan State University
  • 2020.09–2024.06, B.E. in Robotics (Outstanding Graduate), Huazhong University of Science and Technology

💻 Work

  • 2025.05–Present, Research Scientist Intern, ByteDance

🚚 Services

Program Committee/Reviewer

Conferences

  • The International Conference on Machine Learning (ICML)
  • The International Conference on Learning Representations (ICLR)
  • The Annual Conference on Neural Information Processing Systems (Neurips)