arXiv AI By Kun Zhao, Xu Chen

All in One: Generative Modeling as Mean-Field Game Design

Read the original on arXiv AI →

arXiv:2607. 23026v1 Announce Type: cross Abstract: Mean-field games (MFGs) offer a unifying lens on continuous-time generative modeling: a cost tuple recovering twelve prominent models---Continuous Normalizing Flows, OT-Flow, Score-based Models, Schr\"{o}dinger Bridges, and more---as special cases of one variational problem.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning
Jun 9

Midpoint Generative Models

arXiv:2605. 29920v2 Announce Type: replace Abstract: We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models.

By Daniil Shlenskii, Nikita Gushchin, Lev Novitskiy, Dmitry V. Dylov, Alexander Korotin