Midpoint Generative Models Daniil Shlenskii submitted an arXiv paper on 28 May 2026 introducing Midpoint Generative Models (MGM), a framework for training one-step generative models that exploits a symmetry of Flow Matching with linear interpolation: when the two endpoint distributions coincide, the velocity field vanishes at midpoint time t=1/2. The paper defines the norm of that field as the Midpoint Divergence, extends it via randomly flipped interpolations and symmetric stochastic interpolants into a generalized Midpoint Divergence, and derives a tractable variational objective for training a one-step generator. The resulting MGM algorithm is reported to achieve competitive performance against existing one-step generative modeling methods; the paper was last revised on 14 Nov 2026 (v3). Computer Science Machine Learning Submitted on 28 May 2026 v1 https://arxiv.org/abs/2605.29920v1 , last revised 14 Nov 2026 this version, v3 Title:Midpoint Generative Models View PDF https://arxiv.org/pdf/2605.29920 HTML experimental https://arxiv.org/html/2605.29920v3 Abstract:We introduce Midpoint Generative Models MGM , a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow Matching with linear interpolation: when the two endpoint distributions coincide, the corresponding velocity field vanishes at the midpoint time, $t=1/2$. We show that the norm of this field defines a valid discrepancy between distributions, which we call the Midpoint Divergence. We extend this discrepancy beyond the midpoint by introducing randomly flipped interpolations and further generalize it by replacing deterministic linear Flow Matching interpolations with symmetric stochastic interpolants, yielding a generalized Midpoint Divergence. Finally, we derive a variational formulation of our generalized divergence, yielding a tractable objective for training a one-step generator. The resulting MGM algorithm offers an effective and theoretically grounded approach to generative modeling, achieving competitive performance against existing one-step generative modeling methods. Submission history From: Daniil Shlenskii view email https://arxiv.org/show-email/0a219f73/2605.29920 Thu, 28 May 2026 13:31:53 UTC 10,451 KB \ v1\ https://arxiv.org/abs/2605.29920v1 Mon, 8 Jun 2026 13:31:50 UTC 10,593 KB \ v2\ https://arxiv.org/abs/2605.29920v2 v3 Sat, 14 Nov 2026 10:39:31 UTC 20,693 KB Additional Features References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender IArxiv Recommender What is IArxiv? https://iarxiv.org/about arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .