AI RESEARCH
A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models
arXiv CS.AI
•
ArXi:2603.18767v1 Announce Type: new Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches typically rely on keywords to identify the target concept to be unlearned.