Related papers: Latent Ewald summation for machine learning of lon…

Interatomic potentials are key to uncovering microscopic structure-property relationships, essential for multiscale simulations and high-throughput experiments. For metallic glasses, their disordered atomic structure makes the development…

Machine-learned interatomic potentials (MLIPs) based on message passing neural networks hold promise to enable large-scale atomistic simulations of complex materials with ab initio accuracy. A number of MLIPs trained on energies and forces…

As with many parts of the natural sciences, machine learning interatomic potentials (MLIPs) are revolutionizing the modeling of molecular crystals. However, challenges remain for the accurate and efficient calculation of sublimation…

We present two models with explicit long-range electrostatics in the form of Coulomb interactions. Both models include point charges depending on their local atomic environments, and the second model also conserves a total charge of an…

We propose a fast method for the calculation of short-range interactions in molecular dynamics simulations. The so-called random-batch list method is a stochastic version of the classical neighbor-list method to avoid the construction of a…

In recent years, many types of machine learning potentials (MLPs) have been introduced, which are able to represent high-dimensional potential-energy surfaces (PES) with close to first-principles accuracy. Most current MLPs rely on atomic…

When extreme weather events affect large areas, their regional to sub-continental spatial scale is important for their impacts. We propose a novel machine learning (ML) framework that integrates spatial extreme-value theory to model weather…

This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning…

Large molecular dynamics simulations (millions of atoms, tens of microseconds, thousands of processors) hit the strong scalability wall: simulation on twice as many processors does not take half the time. Inspired by large N-body space…

Using extended dynamical mean-field theory and its combination with the $GW$ approximation, we compute the phase diagrams and local spectral functions of the single-band extended Hubbard model on the square and simple cubic lattices,…

Foundation MLIPs demonstrate broad applicability across diverse material systems and have emerged as a powerful and transformative paradigm in chemical and computational materials science. Equivariant MLIPs achieve state-of-the-art accuracy…

Machine learning interatomic potentials (MLIPs) offer near-ab initio accuracy with the efficiency of classical force fields, making them attractive for modeling electrolytes. Collecting a diverse training set is essential for their accuracy…

We consider the problem of identifying stable sets of mutually associated features in moderate or high-dimensional binary data. In this context we develop and investigate a method called Latent Association Mining for Binary Data (LAMB). The…

Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be…

Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics. In this work, a data-driven machine learning algorithm is…

First-principles atomistic simulations are essential for understanding complex material phenomena but are fundamentally limited by their computational cost. While Machine Learning Interatomic Potentials (MLIPs) have drastically improved…

Electronic nearsightedness is one of the fundamental principles governing the behavior of condensed matter and supporting its description in terms of local entities such as chemical bonds. Locality also underlies the tremendous success of…

Pretrained universal machine-learning interatomic potentials (MLIPs) have revolutionized computational materials science by enabling rapid atomistic simulations as efficient alternatives to ab initio methods. Fine-tuning pretrained MLIPs…

High-dimensional multivariate longitudinal data, which arise when many outcome variables are measured repeatedly over time, are becoming increasingly common in social, behavioral and health sciences. We propose a latent variable model for…

Effective interactions between charged particles dispersed in an electrolyte are most commonly modeled using the Derjaguin-Landau-Verwey-Overbeek (DLVO) potential, where the ions in the suspension are coarse-grained out at mean-field level.…