pith. sign in

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 2

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

On Variance Reduction in Learning Mean Flows

cs.LG · 2026-05-10 · unverdicted · novelty 7.0

Deriving the optimal coefficient for the conditional velocity field in MeanFlow training reduces gradient variance and improves sample quality in one-step generative models.

citing papers explorer

Showing 2 of 2 citing papers.

  • On Variance Reduction in Learning Mean Flows cs.LG · 2026-05-10 · unverdicted · none · ref 19

    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 cs.LG · 2026-04-10 · unverdicted · none · ref 38

    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.