A diffusion-based contrastive analysis method that decomposes conditioning into common and salient factors with weak supervision and proves identifiability of the additive model.
Saga: Learning signal-aligned distributions for improved text-to-image generation, 2025
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
-
Diff-CA: Separating Common and Salient Factors with Diffusion Models
A diffusion-based contrastive analysis method that decomposes conditioning into common and salient factors with weak supervision and proves identifiability of the additive model.