Cross-attention maps serve as a tractable surrogate for manifold proximity, enabling automatic synthesis of anchors that suppress normal-space drift in diffusion unlearning.
Semantic surgery: Zero-shot concept erasure in diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
VESFlow edits the learned velocity field of flow matching models via a safe-conditional posterior to produce safe images in 4 sampling steps, with an optional risk filter and VESFlow+ variant that also repels from unsafe directions.
BARRIER applies interval arithmetic to SVD-based activation projections to create bounded forget regions that enable aggressive unlearning while providing formal protection for retain distributions via tail bounds on functional drift.
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.
-
Safe Few-Step Generation via Velocity Editing
VESFlow edits the learned velocity field of flow matching models via a safe-conditional posterior to produce safe images in 4 sampling steps, with an optional risk filter and VESFlow+ variant that also repels from unsafe directions.
-
BARRIER: Bounded Activation Regions for Robust Information Erasure
BARRIER applies interval arithmetic to SVD-based activation projections to create bounded forget regions that enable aggressive unlearning while providing formal protection for retain distributions via tail bounds on functional drift.