AI RESEARCH
SPARE: Self-distillation for PARameter-Efficient Removal
arXiv CS.LG
•
ArXi:2602.07058v2 Announce Type: replace-cross Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data protection regulations and responsible AI practices. Despite recent progress, unlearning in text-to-image diffusion models remains challenging due to high computational costs and the difficulty of balancing effective forgetting with retention of unrelated concepts. We