Interaction Field Matching: Overcoming Limitations of Electrostatic Models
S. I. Manukhov, Alexander Kolesov, V.V. Palyulin, Alexander Korotin
Abstract
Electrostatic field matching (EFM) has recently appeared as a novel physics-inspired paradigm for data generation and transfer using the idea of an electric capacitor. However, it requires modeling electrostatic fields using neural networks, which is non-trivial because of the necessity to take into account the complex field outside the capacitor plates. In this paper, we propose Interaction Field Matching (IFM), a generalization of EFM which allows using general interaction fields beyond the electrostatic one. Furthermore, inspired by strong interactions between quarks and antiquarks in physics, we design a particular interaction field realization which solves the problems which arise when modeling electrostatic fields in EFM. We show the performance on a series of toy and image data transfer problems.
BibTeX
@inproceedings{
manukhov2026interaction,
title={Interaction Field Matching: Overcoming Limitations of Electrostatic Models},
author={S. I. Manukhov and Alexander Kolesov and V.V. Palyulin and Alexander Korotin},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=GEsTLuJy1q}
}