On the Inverse Flow Matching Problem in the One-Dimensional and Gaussian Cases
By: Alexander Korotin, Gudmund Pammer
Potential Business Impact:
Makes AI learn faster and better.
This paper studies the inverse problem of flow matching (FM) between distributions with finite exponential moment, a problem motivated by modern generative AI applications such as the distillation of flow matching models. Uniqueness of the solution is established in two cases - the one-dimensional setting and the Gaussian case. The general multidimensional problem remains open for future studies.
Similar Papers
Provable Mixed-Noise Learning with Flow-Matching
Machine Learning (CS)
Fixes messy data from science experiments.
Saving Foundation Flow-Matching Priors for Inverse Problems
Machine Learning (CS)
Makes AI better at fixing blurry pictures.
On the continuity of flows
Machine Learning (CS)
Makes AI create new things with tricky shapes.