cd /news/machine-learning/midpoint-generative-models · home › topics › machine-learning › article
[ARTICLE · art-173606] src=arxiv.org ↗ pub= topic=machine-learning verified=true sentiment=· neutral

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).

key takeaway

MGM trains a one-step generator by minimizing a variational objective built on the Midpoint Divergence — the norm of the Flow Matching velocity field at t=1/2, where it vanishes when endpoint distributions coincide — and reports competitive performance against existing one-step methods.

read2 min views1 publishedNov 21, 2026
Midpoint Generative Models
Image: source
  [Submitted on 28 May 2026 (

[v1](https://arxiv.org/abs/2605.29920v1)), last revised 14 Nov 2026 (this version, v3)]

[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

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?) alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?) Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?) IArxiv Recommender

(What is IArxiv?) 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.

── more in #machine-learning 4 stories · sorted by recency
── more on @daniil shlenskii 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/midpoint-generative-…] indexed:0 read:2min 2026-11-21 · —