Deriving the optimal coefficient for the conditional velocity field in MeanFlow training reduces gradient variance and improves sample quality in one-step generative models.
Improving and generalizing flow-based generative models with minibatch optimal transport
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
A general framework reduces flow matching on symmetric spaces to flow matching on a Lie algebra subspace, linearizing geodesics.
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.
-
Flow Matching on Symmetric Spaces
A general framework reduces flow matching on symmetric spaces to flow matching on a Lie algebra subspace, linearizing geodesics.