Cross-attention maps serve as a tractable surrogate for manifold proximity, enabling automatic synthesis of anchors that suppress normal-space drift in diffusion unlearning.
One-dimensional adapter to rule them all: Concepts diffusion models and erasing applications
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 2years
2026 2roles
baseline 1polarities
baseline 1representative citing papers
SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.
citing papers explorer
-
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
Cross-attention maps serve as a tractable surrogate for manifold proximity, enabling automatic synthesis of anchors that suppress normal-space drift in diffusion unlearning.
-
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.