pith. sign in

Flow straight and fast: Learning to generate and transfer data with rectified flow

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Distribution Matching Distillation without Fake Score Network

cs.CV · 2026-05-19 · unverdicted · novelty 7.0

FSF-DMD replaces the fake-score network in distribution matching distillation with a generator-induced pseudo-velocity surrogate for flow-map generators, showing improved FID on ImageNet-1K 256x256.

MixFlow: Mixed Source Distributions Improve Rectified Flows

cs.CV · 2026-04-10 · unverdicted · novelty 6.0

Mixing unconditional Gaussian noise with a κ-conditioned source during training of rectified flows reduces path curvature, yielding 12% better FID scores and faster sampling than standard rectified flows.

citing papers explorer

Showing 2 of 2 citing papers.

  • Distribution Matching Distillation without Fake Score Network cs.CV · 2026-05-19 · unverdicted · none · ref 17

    FSF-DMD replaces the fake-score network in distribution matching distillation with a generator-induced pseudo-velocity surrogate for flow-map generators, showing improved FID on ImageNet-1K 256x256.

  • MixFlow: Mixed Source Distributions Improve Rectified Flows cs.CV · 2026-04-10 · unverdicted · none · ref 19

    Mixing unconditional Gaussian noise with a κ-conditioned source during training of rectified flows reduces path curvature, yielding 12% better FID scores and faster sampling than standard rectified flows.