mlsanityData to 7 Oct 2026

A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials

arXiv 2507.14302 ↗First posted 18 Jul 2025physics.chem-ph cs.LG physics.comp-phcited by 9

Not on the map. Why?

Abstract (arXiv)

Most current machine learning interatomic potentials (MLIPs) rely on short-range approximations, without explicit treatment of long-range electrostatics. To address this, we recently developed the Latent Ewald Summation (LES) method, which infers electrostatic interactions, polarization, and Born effective charges (BECs), just by learning from energy and force training data. Here, we present LES as a standalone library, compatible with any short-range MLIP, and demonstrate its integration with methods such as MACE, NequIP, CACE, and CHGNet. We benchmark LES-enhanced models on distinct systems, including bulk water, polar dipeptides, and gold dimer adsorption on defective substrates, and show that LES not only captures correct electrostatics but also improves accuracy. Additionally, we scale LES to large and chemically diverse data by training MACELES-OFF on the SPICE set containing molecules and clusters, making a universal MLIP with electrostatics for organic systems including biomolecules. MACELES-OFF is more accurate than its short-range counterpart (MACE-OFF) trained on the same dataset, predicts dipoles and BECs reliably, and has better descriptions of bulk liquids. By enabling efficient long-range electrostatics without directly training on electrical properties, LES paves the way for electrostatic foundation MLIPs.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 21 of its 86 references that are in the map. First posted on arXiv 18 Jul 2025.

Builds on

21 of 86 references.

References · 21

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  3. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  4. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  5. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  6. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 254
  7. 2020Machine Learning Force Fieldscited by 204
  8. 2022The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalystscited by 95
  9. 2022SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentialscited by 80
  10. 2017DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamicscited by 79
  11. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 79
  12. 2024Open Materials 2024 (OMat24) Inorganic Materials Dataset and Modelscited by 50
9 more
  1. 2023Ewald-based Long-Range Message Passing for Molecular Graphscited by 46
  2. 2024The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domainscited by 40
  3. 2023Smooth, exact rotational symmetrization for deep learning on point cloudscited by 39
  4. 2024Cartesian atomic cluster expansion for machine learning interatomic potentialscited by 31
  5. 2024Latent Ewald summation for machine learning of long-range interactionscited by 26
  6. 2022Capturing long-range interaction with reciprocal space neural networkcited by 13
  7. 2023Physics-inspired Equivariant Descriptors of Non-bonded Interactionscited by 13
  8. 2024Learning charges and long-range interactions from energies and forcescited by 7
  9. 2025Machine learning interatomic potential can infer electrical responsecited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2026A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attentioncited by 7
  2. 2025Spectral/Spatial Tensor Atomic Cluster Expansion with Universal Embeddings in Cartesian Spacecited by 5
  3. 2025Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentialscited by 5
  4. 2025Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spacescited by 2
  5. 2026Polarizable atomic multipoles for learning long-range electrostaticscited by 2
  6. 2025Long-range electrostatics for machine learning interatomic potentials is easier than we thoughtcited by 0
  7. 2026Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentialscited by 0
  8. 2026Distilling latent electrostatics from foundation machine learning interatomic potentialscited by 0
  9. 2026Transferable Implicit Solvent Machine Learning Potential for Drugs and Proteins Approaching Ab Initio Accuracycited by 0