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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace electrostatic field with strong-interaction-inspired field | EFM · CelebA 64x64 generation | FID: >100 -> 3.07 | Improved |
| replace electrostatic field with IFM field | EFM · CIFAR-10 generation | FID: 2.62 -> 2.28 | Improved |
| IFM vs PFGM++ | PFGM++ · CelebA 64x64 generation | FID: 2.89 vs 3.07 | No clear effect |
| add minibatch OT plan to IFM (ablation) | IFM · Winter->Summer translation | CMMD: 1.25 -> 1.13 | Improved |
| add minibatch OT plan to IFM (ablation) | IFM · Colored MNIST 2->3 | CMMD: 0.95 -> 0.87 | Improved |
| increase plate distance L from 6 to 40 (ablation) | IFM · Gaussian to Swiss Roll | qualitative transfer quality | No clear effect |
| IFM vs EFM translation | EFM · Winter->Summer translation | CMMD: EFM >>1 vs 1.25 | Improved |
Closest papers by meaning
- Field Matching: an Electrostatic Paradigm to Generate and Transfer Data (ICML 2025 · similarity 0.91)
- Learning from Integral Losses in Physics Informed Neural Networks (ICML 2024 · similarity 0.82)
- End-to-End Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning (AAAI 2024 · similarity 0.81)
- The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains (NeurIPS 2024 · similarity 0.80)
- Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing (NeurIPS 2024 · similarity 0.80)
- EDBench: Large-Scale Electron Density Data for Molecular Modeling (NeurIPS 2025 · similarity 0.80)
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.
