A training-free double-projection linear transformation erases target concepts from generative models by computing a proxy projection then applying a constrained update in the left null space of known directions.
A single neuron works: Precise concept erasure in text-to-image diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
citing papers explorer
-
Closed-Form Concept Erasure via Double Projections
A training-free double-projection linear transformation erases target concepts from generative models by computing a proxy projection then applying a constrained update in the left null space of known directions.
-
Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.