Expert disagreement inside pretrained MoE diffusion models, measured as latent variance at the first denoising step, gives a training-free prompt uncertainty signal that correlates with text-image alignment across languages.
Shedding light on large generative networks: Estimating epistemic uncertainty in diffusion models
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.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion
Expert disagreement inside pretrained MoE diffusion models, measured as latent variance at the first denoising step, gives a training-free prompt uncertainty signal that correlates with text-image alignment across languages.