AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Multi-Marginal Flow Matching with Adversarially Learnt Interpolants

Oskar Kviman, Kirill Tamogashev, Nicola Branchini, Víctor Elvira, Jens Lagergren, Nikolay Malkin

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adversarially learnt interpolants instead of piecewise linear interpolants (OT-CFM)OT-CFM · spatial transcriptomicsEMD: 109.76 -> 98.91Improved
use adversarially learnt interpolants instead of the LAND-metric interpolants (OT-MFM)OT-MFM · spatial transcriptomicsEMD: 183.88 -> 98.91Improved
use ALI instead of OT-CFM on Cite 5DOT-CFM · Cite scRNA-seq (5D PCA)EMD: 1.142 -> 0.910Improved
use ALI instead of OT-CFM on EB 5DOT-CFM · EB scRNA-seq (5D PCA)EMD: 0.809 -> 0.742Improved
use ALI instead of OT-MFM on Cite 5DOT-MFM · Cite scRNA-seq (5D PCA)EMD: 0.793 -> 0.910Hurt
use ALI instead of cubic spline interpolants (OT-MMFM) on EB 5DOT-MMFM · EB scRNA-seq (5D PCA)EMD: 3.530 -> 0.742Improved
use ALI instead of OT-MFM on Cite 50DOT-MFM · Cite scRNA-seq (50D PCA)EMD: 36.471 -> 41.449Hurt
use ALI instead of OT-CFM on Cite 50DOT-CFM · Cite scRNA-seq (50D PCA)EMD: 38.367 -> 41.449Hurt
use ALI instead of OT-CFM on Multi 100DOT-CFM · Multi scRNA-seq (100D PCA)EMD: 54.630 -> 54.554No clear effect
increase piecewise-linear regulariser coefficient lambda from 0.01 to 0.05 (ablation)OT-ALI-CFM · Cite 50D, left-out t=1CFM EMD: 47.29 -> 41.07Improved
increase piecewise-linear regulariser coefficient lambda from 0.01 to 10 (ablation)OT-ALI-CFM · Cite 50D, left-out t=1CFM path energy: 300.01 -> 87052.14Hurt
increase second-derivative regulariser coefficient from 1e-9 to 1e-6 (ablation)OT-ALI-CFM · Cite 50D, left-out t=1CFM path energy: 56.39 -> 12.30Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy