Chongyu Fan
- Papers
- 7
Cite
Notes
Only stored in your browser.
Authored papers
7Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
arXiv 2026
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
arXiv 2025
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
arXiv 2024
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
arXiv 2024
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
arXiv 2024
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
arXiv 2024
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
arXiv 2023
Affiliations
Frequent co-authors
10from 7 papers