Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
Sta- ble target field for reduced variance score estimation in diffusion models.arXiv preprint arXiv:2302.00670,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 4roles
background 1polarities
background 1representative citing papers
TM outperforms FM for well-separated modes with non-negligible variance by preserving covariance via stochastic latent updates, with the gap closing as variance approaches zero.
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
A DMF curriculum initialized from pretrained flow models achieves one-step FID 3.36 on CIFAR-10 after only 2000 epochs by exploiting a discretized consistency property in the Meanflow objective.
citing papers explorer
-
Generative Modeling with Flux Matching
Flux Matching generalizes score-based generative modeling by using a weaker objective that admits infinitely many non-conservative vector fields with the data as stationary distribution, enabling new design choices beyond traditional score matching.
-
Demystifying Transition Matching: When and Why It Can Beat Flow Matching
TM outperforms FM for well-separated modes with non-negligible variance by preserving covariance via stochastic latent updates, with the gap closing as variance approaches zero.
-
Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
-
Discrete Meanflow Training Curriculum
A DMF curriculum initialized from pretrained flow models achieves one-step FID 3.36 on CIFAR-10 after only 2000 epochs by exploiting a discretized consistency property in the Meanflow objective.