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.
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
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
EquiSteer reduces average demographic parity gaps by up to 87% in Stable Diffusion variants and SANA via inference-time cross-attention steering with minimal impact on image quality or alignment.
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.
-
EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation
EquiSteer reduces average demographic parity gaps by up to 87% in Stable Diffusion variants and SANA via inference-time cross-attention steering with minimal impact on image quality or alignment.