A sparse set of massive activation channels in DiTs carries semantic information, proven critical by disruption tests, spatially aligned with image subjects via clustering, and transferable for semantic interpolation between prompts.
All are Worth Words: A ViT Backbone for Diffusion Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
A sparse set of massive activation channels in DiTs carries semantic information, proven critical by disruption tests, spatially aligned with image subjects via clustering, and transferable for semantic interpolation between prompts.