ReToM merges tokens around a similarity-selected representative token in adaptive local windows, improving Stable Diffusion FID from 37.02 to 34.89 at comparable inference speed.
Generative adversarial networks,
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Local Representative Token Guided Merging for Text-to-Image Generation
ReToM merges tokens around a similarity-selected representative token in adaptive local windows, improving Stable Diffusion FID from 37.02 to 34.89 at comparable inference speed.