AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Interaction Field Matching: Overcoming Limitations of Electrostatic Models

S. I. Manukhov, Alexander Kolesov, V.V. Palyulin, Alexander Korotin

ICLR 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Physics-informed dynamics learning

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
replace electrostatic field with strong-interaction-inspired fieldEFM · CelebA 64x64 generationFID: >100 -> 3.07Improved
replace electrostatic field with IFM fieldEFM · CIFAR-10 generationFID: 2.62 -> 2.28Improved
IFM vs PFGM++PFGM++ · CelebA 64x64 generationFID: 2.89 vs 3.07No clear effect
add minibatch OT plan to IFM (ablation)IFM · Winter->Summer translationCMMD: 1.25 -> 1.13Improved
add minibatch OT plan to IFM (ablation)IFM · Colored MNIST 2->3CMMD: 0.95 -> 0.87Improved
increase plate distance L from 6 to 40 (ablation)IFM · Gaussian to Swiss Rollqualitative transfer qualityNo clear effect
IFM vs EFM translationEFM · Winter->Summer translationCMMD: EFM >>1 vs 1.25Improved

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