ljcc0930/awesome-machine-unlearning

Awesome Machine Unlearning (A Survey of Machine Unlearning)

Hi there 👋

My name is Jiancheng (JC) Liu. I am a graduate student at Michigan State University, currently work at OPTML Group. My recent research focuses on scalable and trustworthy AI.

• I am planning to enroll as a doctoral student in 2025. Should you have any promising opportunities, please feel free to contact me!

My recent works about machine unlearning (MU)

Paper Title	Venue	Repository
Unlearning for LLMs
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning	In Submission	(TBA)
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models	NeurIPS'24	(TBA)
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning	EMNLP'24
Unlearning for Diffusion Models
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models	NeurIPS'24
UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models	NeurIPS'24 D&B
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images... For Now	ECCV'24
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation	ICLR'24 (Spotlight)
Unlearning for Classification Models
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning	ECCV'24
Model Sparsity Can Simplify Machine Unlearning	NeurIPS'23 (Spotlight)