A pairwise-conditioned diffusion model generates instructional illustrations from procedural text and is finetuned with a text-image alignment reward.
https://api.semanticscholar.org/CorpusID:264403242 Improving image generation with better captions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion
A pairwise-conditioned diffusion model generates instructional illustrations from procedural text and is finetuned with a text-image alignment reward.