2025
CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
NeurIPS 2025spotlight
As Text-to-Image models continue to evolve, so does the risk of generating unsafe, copyrighted, or privacy-violating content. Existing safety interventions - ranging from training data curation and model fine-tuning to inference-time filtering and guidance - often suffer from incomplete concept remo…