Föllmer processes are variationally optimal among generative diffusions because they minimize the impact of drift estimation error on path-space KL divergence, rendering different interpolation schedules statistically equivalent.
Stochastic interpolants: A unifying framework for flows and diffusions.Journal of Machine Learning Research, 26(209):1–80
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
FREPix achieves competitive FID scores on ImageNet by decomposing image generation into separate low- and high-frequency paths within a flow matching framework.
citing papers explorer
-
Variational Optimality of F\"ollmer Processes in Generative Diffusions
Föllmer processes are variationally optimal among generative diffusions because they minimize the impact of drift estimation error on path-space KL divergence, rendering different interpolation schedules statistically equivalent.
-
FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
FREPix achieves competitive FID scores on ImageNet by decomposing image generation into separate low- and high-frequency paths within a flow matching framework.
- Coreset-Induced Conditional Velocity Flow Matching