arXiv:2508. 05762v2 Announce Type: replace-cross Abstract: Universal machine learning force fields (UMLFFs) promise to revolutionize materials science by enabling rapid atomistic simulations across the periodic table.
arXiv:2606. 18691v1 Announce Type: new Abstract: Pre-trained materials foundation models, or machine learning interatomic potentials, leverage general physicochemical knowledge to effectively approximate potential energy surfaces.
The paper introduces a benchmark to evaluate compositional generalisation in machine learning interatomic potentials. It comprises four tasks that test models on unseen molecules, designed so that learning underlying chemical principles should enable generalisation. Experiments show that current state‑of‑the‑art models struggle, with out‑of‑distribution errors often an order of magnitude higher than in‑distribution errors, even for foundation models pre‑trained on millions of molecules.
The paper introduces UniTB, a universal, E(3)-equivariant Hamiltonian framework that blends density‑functional tight‑binding priors with deep learning to predict electronic structures efficiently. UniTB corrects a prior Hamiltonian via a mixture‑of‑experts network and a charge‑equilibration head, ensuring physical downstream properties and suppressing spurious states. Trained on over 29,000 crystals, UniTB achieves sub‑meV accuracy, matches DFT predictions for amorphous Ge‑Sb‑Te, and enables rapid screening of more than 16,000 materials for industrial applications.
The paper presents a multitask learning approach that incorporates orbitally resolved semiempirical charges into machine learning interatomic potentials (MLIPs). By training with inexpensive GFN1‑xTB orbital charges, the model reduces energy mean absolute error by 58% compared to energy‑only baselines and needs five times less data to achieve similar performance. The method also outperforms or matches models using costly DFT charges and preserves inference efficiency, offering a scalable way to build accurate, data‑efficient foundation models for complex chemical systems.
arXiv:2610.08020v1 Announce Type: cross Abstract: Classical force fields (FFs) remain the workhorse for large-scale simulations even as machine-learned interatomic potentials (MLIPs) approach ab init...
arXiv:2606. 06765v1 Announce Type: cross Abstract: Establishing quantitative relationships among mix design, raw material properties, curing conditions, and performance remains a long-standing challenge in cementitious materials, particularly for alkali-activated materials with variable precursor and activator chemistry.
Machine-learned interatomic potentials (MLIPs) excel at in-distribution tasks, accelerating drug and material development, yet they struggle to generalize out-of-distribution. We propose to push the c...
The paper introduces Physics‑Aligned Electronic Ground‑State Models (GSMs) that sit between machine‑learned interatomic potentials and Kohn‑Sham density functional theory in terms of computational cost and accuracy. By aligning GSM learning objectives with KS‑DFT equations and enforcing physical constraints, the authors develop new training techniques—OrthoNormal‑Loss (ON‑Loss), Grassmann Restricted Occupied‑Orbital Training (GROOT), and Residual Optimal‑gauge Conditioning‑aware KS‑Eq. Training (ROCKET)—which dramatically reduce energy and force errors in size‑extrapolation tests from QM9 to QM40. The models also achieve near‑chemical‑accuracy predictions on reactive chemistry benchmarks and demonstrate efficient label‑free self‑consistency fine‑tuning. whyItMatters":"The work advances the cost‑accuracy frontier for electronic structure predictions, enabling more reliable out‑of‑distribution generalization in drug and material discovery."
arXiv:2606. 15001v1 Announce Type: cross 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.
The study shows that electronic structure datasets used for machine learning contain significant redundancy due to low intrinsic dimensionality. Random pruning and a coverage-based strategy can reduce dataset size by up to two orders of magnitude while preserving chemical accuracy and generalizability, cutting training time by a factor of three or more. The essential information lies on a low‑dimensional, non‑linear manifold, suggesting that large datasets may be largely overlapping and that minimal, representative datasets could suffice for accurate predictions.
The paper presents a hyperreduction technique that accelerates finite element model updating for discovering neural constitutive models from structural experiments. By combining proper orthogonal decomposition, energy‑conserving sampling, and adjoint sensitivities, the method adapts the reduced trial space and sampled elements during training, enabling a polyconvex neural network to maintain accuracy while drastically reducing computational cost. Experiments on two experimental datasets and a synthetic 3‑D example show training times drop from hours to minutes without sacrificing predictive fidelity.