DECOR suppresses undesired word-token semantics in text embeddings via orthogonal projection, reducing prompt misalignment and content leakage in LoRA-customized text-to-image models.
Muse: Text- to-image generation via masked generative transformers.Pro- ceedings of the 40th International Conference on Machine Learning, 202, 2023
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization
DECOR suppresses undesired word-token semantics in text embeddings via orthogonal projection, reducing prompt misalignment and content leakage in LoRA-customized text-to-image models.