Deriving the optimal coefficient for the conditional velocity field in MeanFlow training reduces gradient variance and improves sample quality in one-step generative models.
Simplifying, stabilizing and scaling continuous-time consistency models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
JFDL allows pre-trained Consistency Models to perform guided image generation post-hoc by aligning flow distributions, reducing FID scores on CIFAR-10 and ImageNet without needing a teacher model.
citing papers explorer
-
On Variance Reduction in Learning Mean Flows
Deriving the optimal coefficient for the conditional velocity field in MeanFlow training reduces gradient variance and improves sample quality in one-step generative models.
-
Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
JFDL allows pre-trained Consistency Models to perform guided image generation post-hoc by aligning flow distributions, reducing FID scores on CIFAR-10 and ImageNet without needing a teacher model.