AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Multimarginal flow matching with optimal transport potentials

Raghav Kansal, David Crair, Nghia D. Nguyen, Scott D Pope, Bradley R Parry

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 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 W2^2 potential instead of W2^inf (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.0813 -> 0.0675Improved
use W2^2 potential instead of MMD potential (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.0861 -> 0.0675Improved
use W2^2 potential instead of KL potential (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.0876 -> 0.0675Improved
raise potential strength from w=10 to w=1000 (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.1431 -> 0.0675Improved
raise potential strength from w=1000 to w=10000 (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.0675 -> 0.0683No clear effect
use Gaussian window instead of triangle (ablation)OTP-FM lambda(t) · EB 100D L2Omean MMD on held-out times: 0.0723 -> 0.0675Improved
use Gaussian window instead of box (ablation)OTP-FM lambda(t) · EB 100D L2Omean MMD on held-out times: 0.0681 -> 0.0675No clear effect
use sigmoid curriculum instead of linear (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.0800 -> 0.0675Improved
use sigmoid curriculum instead of constant (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.0687 -> 0.0675Improved
shift sigmoid midpoint to mu=1 (ablation)OTP-FM curriculum · EB 100D L2Omean MMD on held-out times: 0.0675 -> 0.0758Hurt
vary window width tau between 0.2 and 0.5 (ablation)OTP-FM · EB 100D L2Omean MMD on held-out times: 0.0690, 0.0675, 0.0693No clear effect
use OTP-FM (W2^2) instead of MMFMtrajectory model · Gulf of Mexico (2D, 9 timepoints)held-out average W2: 0.150 -> 0.107Improved

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