The paper introduces ADAPT, a lightweight machine‑learning force field that replaces graph neural networks with a direct coordinates‑in‑space Transformer encoder to model all pairwise atomic interactions. Applied to silicon point defects, ADAPT reduces force prediction error by about 22% and energy prediction error by roughly 40% compared to a state‑of‑the‑art GNN model, while also cutting computational cost. This approach addresses common GNN issues such as oversmoothing, oversquashing, and poor long‑range interaction representation, which are especially problematic for point defect modeling.
arXiv:2606. 03232v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have revolutionized Neural Force Fields for atomistic simulations, achieving near-quantum accuracy at reduced cost, yet adapting these models to new chemical systems requires expensive retraining of foundation models.
arXiv:2607. 29158v1 Announce Type: cross Abstract: We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations.
The paper introduces two Hessian-based data augmentation techniques—UniAug and ModeAug—to improve machine‑learning interatomic potentials (MLIPs). These methods use simple Taylor expansions to generate augmented configurations without modifying training objectives or increasing computational overhead. Experiments on both non‑equilibrium and equilibrium datasets show that the augmentations enhance model accuracy and provide practical guidelines for specific tasks.
The paper investigates whether machine learning models can uncover physical patterns in atomistic data without relying on traditional physics-based inductive biases such as geometric locality or graph structures. By training a general-purpose architecture on molecular simulation data, the authors demonstrate that the model autonomously learns interatomic interaction strengths resembling classical electrostatics and identifies interaction cutoffs aligned with established physical models. The study also reports predictable neural scaling behavior and competitive accuracy on certain metrics compared to physics-informed architectures, suggesting that explicit priors may only be necessary when empirically justified.
arXiv:2606. 00776v1 Announce Type: new Abstract: Fast and accurate prediction of crystal properties is a central challenge in new materials design.
arXiv:2607. 24818v1 Announce Type: cross Abstract: Accurate prediction of crystal properties remains a key challenge in computational materials science.
arXiv:2509.21624v4 Announce Type: replace Abstract: Molecular Hessians, the second derivatives of the potential energy, are fundamental to many workflows in computational chemistry. Usually, accurate...
arXiv:2509. 21624v3 Announce Type: replace Abstract: Fundamental tasks in computational chemistry, from transition state search to vibrational analysis, rely on molecular Hessians, which are the second derivatives of the potential energy.
The paper presents physics‑guided machine‑learning models that predict defect formation energies and zero‑phonon lines (ZPLs) for point defects in semiconductors, aiming to replace costly density‑functional theory (DFT) calculations in the prescreening stage of high‑throughput workflows. Using ridge, kernel ridge, and multilayer perceptron models with three descriptors, the authors achieve mean absolute errors of 0.437 eV for formation energies and 0.202 eV for ZPLs on vacancies and substitutions in 4H‑SiC, while interstitials show larger errors (1.101 eV and 0.230 eV). These results demonstrate that the models can effectively accelerate defect screening, potentially obviating the need for expensive DFT relaxations in many cases.
arXiv:2507. 03853v2 Announce Type: replace Abstract: We introduce OrbitAll, a geometry- and physics-informed deep learning framework that encodes any molecular system with arbitrary charges, spins, and environmental effects using electronic structure information.
arXiv:2606. 05116v1 Announce Type: new Abstract: We introduce the Graph Set Transformer (GST), a neural network architecture for learning on sets of graphs, designed for tasks in which per-element predictions depend on set-wide context as well as local structure.
MeshGraphNet-Transformer (MGN‑T) is a new architecture that fuses Transformers’ global modeling with MeshGraphNets’ geometric inductive bias, keeping a mesh‑based graph representation. It replaces iterative message passing with a physics‑attention Transformer that updates all nodal states simultaneously, enabling efficient learning on high‑resolution meshes with diverse geometries, topologies, and boundary conditions. MGN‑T accurately models impact dynamics, self‑contact, plasticity, and multivariate outputs, outperforming state‑of‑the‑art methods on classical benchmarks while using far fewer parameters.