Dynamic Eraser for Guided Concept Erasure in Diffusion Models

arXiv:2604.16483v1 Announce Type: cross Abstract: Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while token-level interventions struggle with semantic granularity and context. Moreover, both types of methods are prone to severe semantic drift or even complete representation collapse. To address these challenges,