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.
Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks.Journal of Machine Learning Research, 22(241):1–124
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
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.