Artificial intelligence for science in quantum, atomistic, and continuum systems

X Zhang, L Wang, J Helwig, Y Luo, C Fu, Y **e… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …

Spatio-spectral graph neural networks

SM Geisler, A Kosmala, D Herbst… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
Abstract Spatial Message Passing Graph Neural Networks (MPGNNs) are widely used for
learning on graph-structured data. However, key limitations of ℓ-step MPGNNs are that their" …

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

A Nicolle, S Deng, M Ihme… - Journal of Chemical …, 2024‏ - ACS Publications
Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures,
providing an expressive view of the chemical space and multiscale processes. Their …

The Potential of Neural Network Potentials

TT Duignan - ACS Physical Chemistry Au, 2024‏ - ACS Publications
In the next half-century, physical chemistry will likely undergo a profound transformation,
driven predominantly by the combination of recent advances in quantum chemistry and …

Active learning graph neural networks for partial charge prediction of metal-organic frameworks via dropout Monte Carlo

S Thaler, F Mayr, S Thomas, A Gagliardi… - npj Computational …, 2024‏ - nature.com
Metal-organic frameworks (MOF) are an attractive class of porous materials due to their
immense design space, allowing for application-tailored properties. Properties of interest …

Long-short-range message-passing: A physics-informed framework to capture non-local interaction for scalable molecular dynamics simulation

Y Li, Y Wang, L Huang, H Yang, X Wei, J Zhang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Computational simulation of chemical and biological systems using ab initio molecular
dynamics has been a challenge over decades. Researchers have attempted to address the …

Efficient machine learning force field for large-scale molecular simulations of organic systems

J Hu, L Zhou, J Jiang - CCS Chemistry, 2024‏ - chinesechemsoc.org
To address the computational challenges of ab initio molecular dynamics and the accuracy
limitations of empirical force fields, the introduction of machine learning force fields (MLFFs) …

Latent Ewald summation for machine learning of long-range interactions

B Cheng - arxiv preprint arxiv:2408.15165, 2024‏ - arxiv.org
Machine learning interatomic potentials (MLIPs) often neglect long-range interactions, such
as electrostatic and dispersion forces. In this work, we introduce a straightforward and …

Modeling Zinc Complexes Using Neural Networks

H **, KM Merz Jr - Journal of Chemical Information and Modeling, 2024‏ - ACS Publications
Understanding the energetic landscapes of large molecules is necessary for the study of
chemical and biological systems. Recently, deep learning has greatly accelerated the …

Implicit transfer operator learning: multiple time-resolution surrogates for molecular dynamics

M Schreiner, O Winther, S Olsson - arxiv preprint arxiv:2305.18046, 2023‏ - arxiv.org
Computing properties of molecular systems rely on estimating expectations of the
(unnormalized) Boltzmann distribution. Molecular dynamics (MD) is a broadly adopted …