Interaction Field Matching: Overcoming Limitations of Electrostatic Models

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.

Cite

Text

Manukhov et al. "Interaction Field Matching: Overcoming Limitations of Electrostatic Models." International Conference on Learning Representations, 2026.

Markdown

[Manukhov et al. "Interaction Field Matching: Overcoming Limitations of Electrostatic Models." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/manukhov2026iclr-interaction/)

BibTeX

@inproceedings{manukhov2026iclr-interaction,
  title     = {{Interaction Field Matching: Overcoming Limitations of Electrostatic Models}},
  author    = {Manukhov, S. I. and Kolesov, Alexander and Palyulin, V.V. and Korotin, Alexander},
  booktitle = {International Conference on Learning Representations},
  year      = {2026},
  url       = {https://mlanthology.org/iclr/2026/manukhov2026iclr-interaction/}
}