SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation Paper • 2310.12508 • Published Oct 19, 2023 • 1
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models Paper • 2405.15234 • Published May 24, 2024 • 1
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning Paper • 2403.07362 • Published Mar 12, 2024 • 1
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning Paper • 2410.07163 • Published Oct 9, 2024 • 2
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Paper • 2502.05374 • Published Feb 7 • 1
CyclicReflex: Improving Large Reasoning Models via Cyclical Reflection Token Scheduling Paper • 2506.11077 • Published Jun 4 • 1