Distilling latent electrostatics from foundation machine learning interatomic potentials

• URL: http://arxiv.org/abs/2606.15001v1
• Date: Fri, 12 Jun 2026 22:45:20 GMT
• Title: Distilling latent electrostatics from foundation machine learning interatomic potentials
• Abstract summary: Latent Ewald Summation (LES) learns latent atomic charges and long-range electrostatics from density functional theory energy and force labels alone.<n>We benchmark student models distilled from a broad set of foundation MLIPs, including UMA, MACE, Orb, eSEN, GemNet-OC, PET, and EquiformerV2-based models.<n>LES-based distillation provides a practical route for converting foundation MLIPs into efficient, electrically responsive models.
• Score: 4.208220582996209
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation machine learning interatomic potentials (MLIPs) have enabled atomistic simulations across broad regions of chemical and materials space, but many remain computationally expensive and lack explicit electrostatics, limiting their use for systems governed by long-range interactions and electrical response. Previously, we introduced Latent Ewald Summation (LES), which learns latent atomic charges and long-range electrostatics from density functional theory (DFT) energy and force labels alone. Here, we use LES to extract electrostatics that are latent in foundation models: energies and forces predicted by a teacher model are used to train a lightweight LES-augmented student MLIP, with optional fine-tuning on additional DFT data. The resulting models reduce computational cost while providing access to Born effective charge tensors, and infrared spectra. We benchmark student models distilled from a broad set of foundation MLIPs, including UMA, MACE, Orb, eSEN, GemNet-OC, PET, and EquiformerV2-based models, against experimental infrared spectra for liquid water, concentrated hydrochloric acid, and the anatase TiO2(101)-water interface. Across these systems, electrostatic response can be extracted from most foundation MLIPs. The benchmark further shows that the underlying DFT level and dataset used to train the teacher model play a larger role than architecture in determining electrostatic and spectroscopic accuracy. For the TiO2-water interface, fine-tuning with a modest amount of higher-level DFT data improves structural and infrared predictions. LES-based distillation therefore provides a practical route for converting foundation MLIPs into efficient, electrically responsive models, while also testing the physical fidelity encoded in foundation models.

Related papers

• Ab initio Modeling of MoS2/Oxide Device Interfaces with Machine Learned Electronic Structures [66.44589802420899]
  We introduce a new ab initio approach to simulate semiconductor devices that integrates scalable machine-learned (ML) electronic structure models with an advanced quantum transport (QT) solver.<n>The framework enables 10,000X speedups over density functional theory to produce the Hamiltonian matrix of devices made of >20,000 atoms.
  arXiv  Detail & Related papers  (2026-08-27T15:33:39Z)
• EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation [54.09734511705173]
  EFF-Grasp is a Flow-Matching synthesis-based framework for physics-aware dexterous grasp generation.<n>We reformulate grasp as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows.<n> EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-03-17T06:11:56Z)
• From Static Spectra to Operando Infrared Dynamics: Physics Informed Flow Modeling and a Benchmark [67.29937933325849]
  Operando IR Prediction aims to forecast the time-resolved evolution of spectral fingerprints'' from a single static spectrum.<n>OpIRSpec-7K comprises 7,118 high-quality samples across 10 distinct battery systems.<n>ABCC significantly outperforms state-of-the-art static, sequential, and generative baselines.
  arXiv  Detail & Related papers  (2026-02-20T18:58:43Z)
• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials [8.414405667524889]
  Latent Ewald Summation (LES) method infers electrostatic interactions, polarization, and Born effective charges (BECs)<n>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.<n>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.
  arXiv  Detail & Related papers  (2025-07-18T18:21:45Z)
• Machine learning interatomic potential can infer electrical response [3.502816712907136]
  Machine learning interatomic potentials (MLIPs) offer an efficient and scalable alternative to quantum mechanical methods.<n>We show that polarization and Born effective charge (BEC) tensors can be directly extracted from long-range MLIPs.<n>This work extends the capability MLIPs to predict electrical response--without training on charges or polarization or BECs--and enables accurate modeling of electric-field-driven processes in diverse systems at scale.
  arXiv  Detail & Related papers  (2025-04-07T15:14:07Z)
• Ensemble Knowledge Distillation for Machine Learning Interatomic Potentials [34.82692226532414]
  We present an ensemble knowledge distillation (EKD) method to improve machine learning interatomic potentials (MLIPs)<n>First, multiple teacher models are trained to QC energies and then generate atomic forces for all configurations in the dataset. Next, the student MLIP is trained to both QC energies and to ensemble-averaged forces generated by the teacher models.<n>The resulting student MLIPs achieve new state-of-the-art accuracy on the COMP6 benchmark and show improved stability for molecular dynamics simulations.
  arXiv  Detail & Related papers  (2025-03-18T14:32:51Z)
• Predicting ionic conductivity in solids from the machine-learned potential energy landscape [68.25662704255433]
  We propose an approach for the quick and reliable screening of ionic conductors through the analysis of a universal interatomic potential.<n>Eight out of the ten highest-ranked materials are confirmed to be superionic at room temperature in first-principles calculations.<n>Our method achieves a speed-up factor of approximately 50 compared to molecular dynamics driven by a machine-learning potential, and is at least 3,000 times faster compared to first-principles molecular dynamics.
  arXiv  Detail & Related papers  (2024-11-11T09:01:36Z)
• Multi-task learning for molecular electronic structure approaching coupled-cluster accuracy [9.81014501502049]
  We develop a unified machine learning method for electronic structures of organic molecules using the gold-standard CCSD(T) calculations as training data. Tested on hydrocarbon molecules, our model outperforms DFT with the widely-used hybrid and double hybrid functionals in computational costs and prediction accuracy of various quantum chemical properties.
  arXiv  Detail & Related papers  (2024-05-09T19:51:27Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)
• Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks [2.7035666571881856]
  We present a numerical modeling workflow based on machine learning (ML) which reproduces the the total energies produced by Kohn-Sham density functional theory (DFT) at finite electronic temperature. Based on deep neural networks, our workflow yields the local density of states (LDOS) for a given atomic configuration. We demonstrate the efficacy of this approach for both solid and liquid metals and compare results between independent and unified machine-learning models for solid and liquid aluminum.
  arXiv  Detail & Related papers  (2020-10-10T05:38:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.