Cross-attention maps serve as a tractable surrogate for manifold proximity, enabling automatic synthesis of anchors that suppress normal-space drift in diffusion unlearning.
The intrinsic dimension of images and its impact on learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Self-supervised encoders prefer isotropic Gaussian latent states because the Information Bottleneck, recast as rate-distortion over the predictive manifold, makes these states optimal for target-neutral representations.
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.
-
Why Self-Supervised Encoders Want to Be Normal
Self-supervised encoders prefer isotropic Gaussian latent states because the Information Bottleneck, recast as rate-distortion over the predictive manifold, makes these states optimal for target-neutral representations.