By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
Saco loss: Sample-wise affinity consistency for vision-language pre-training
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
-
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.