SAEs detect concepts well in diffusion models but fail as direct intervention points for unlearning; a detection-guided patch replacement method yields significantly cleaner erasure results.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
citing papers explorer
-
Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models
SAEs detect concepts well in diffusion models but fail as direct intervention points for unlearning; a detection-guided patch replacement method yields significantly cleaner erasure results.
-
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.