Chongyu Fan
Scholar

Chongyu Fan

Google Scholar ID: GLtCYtgAAAAJ
Michigan State University
Post trainingAlignment
Citations & Impact
All-time
Citations
465
 
H-index
6
 
i10-index
6
 
Publications
12
 
Co-authors
6
list available
Resume (English only)
Academic Achievements
  • NeurIPS 2025: First-author paper 'Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning' (SimNPO) accepted
  • EMNLP 2025 Main: First-author paper 'Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills' (Reasoning Unlearn) accepted
  • ICML 2025: First-author paper 'Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond' (Smooth Unlearn) accepted
  • ECCV 2024: First-author paper 'Challenging Forgets: Unveiling the Worst-case Forget Sets in Machine Unlearning' accepted
  • ICLR 2024 Spotlight: First-author paper 'SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation' accepted
  • NeurIPS 2024: Two papers 'UnlearnCanvas' and 'AdvUnlearn' accepted
  • June 2025: First-author paper 'CyclicReflex' and co-authored paper 'EPiC' posted on arXiv
  • Serving as Program Committee member / reviewer for ICML, ICLR, and NeurIPS