y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#concept-unlearning News & Analysis

1 article tagged with #concept-unlearning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AIBullisharXiv – CS AI · 5h ago6/10
🧠

SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders

Researchers introduce SAEmnesia, a supervised sparse autoencoder framework that enables efficient concept unlearning in diffusion models by binding concepts to individual neurons. The method reduces computational overhead by 96.67% compared to existing approaches and achieves 9.22% improvement on benchmark tests, with demonstrated robustness against adversarial attacks.