The paper introduces a machine‑learning approach that incorporates the ground‑state electron density as input while enforcing it to be the minimum of a surrogate functional derived from orbital‑free density functional theory. This method outperforms state‑of‑the‑art models on six of seven extensive properties in the QM9 dataset and shows better generalization to larger molecules in the QM40 dataset. Models that use the density without enforcing the surrogate functional constraints perform worse on all extensive properties of both datasets.
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:2607. 18281v1 Announce Type: cross Abstract: Finding exact solutions to the quantum many-body problem is computationally intractable (QMA-hard).
arXiv:2605.24073v2 Announce Type: replace-cross Abstract: Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately sim...
arXiv:2606. 17077v1 Announce Type: cross Abstract: Proton dissociation constants (pKa) are critical for functional molecule discovery and molecular modeling.
The paper introduces OrbFlow, an SE(3)-equivariant generative model that predicts Gaussian-type orbital coefficients for electron density using flow matching. By training with a two-phase trajectory curriculum, OrbFlow improves accuracy on QM9 and MD benchmarks, reducing density errors significantly compared to previous models. The predicted densities also accelerate self-consistent field procedures, cutting iterations by up to 68% and accurately reproducing dipole and quadrupole moments without additional SCF calculations.
The article discusses how machine learning potentials (MLPs) can surpass the accuracy of the quantum‑chemical methods they are trained on by generalizing across a third space—different quantum‑chemical methods. It proposes the development of method‑transferable MLPs that predict properties at unseen methods, demonstrating that such models can outperform any of their training methods in both density‑functional and wavefunction‑based theories. The authors argue that pursuing accuracy beyond the training methods could enable universal MLPs to exceed single‑method models, influencing dataset construction and model evaluation to push chemical simulation limits.
arXiv:2606. 14498v1 Announce Type: cross Abstract: Predicting the Kohn-Sham Hamiltonian with machine learning can accelerate density functional theory while retaining access to molecular orbitals, energy levels, and electronic-structure observables that energy-only surrogates cannot resolve.
The study compares two machine‑learning approaches for predicting molecular absorption spectra: one that uses the ground‑state electron density as input and another that uses molecular geometry. Using a dataset of 6,874 molecules from QM7, the density‑based convolutional neural network achieved a higher validation correlation (0.9926) than the best geometry‑based graph model (0.9795), reducing residual decorrelation by about 64%. The authors argue that the density, which encodes bonding, charge localisation, and electronic delocalisation, provides a more informative starting point for ML models despite the modest cost of an additional DFT calculation. whyItMatters":"The results suggest that incorporating ground‑state electron density into ML models can significantly improve the accuracy of predicted absorption spectra, potentially enabling faster and more reliable spectroscopic analysis of large molecular libraries."
BOOM is a new benchmark for evaluating out‑of‑distribution (OOD) molecular property predictions in machine learning. It provides chemically‑informed tests across common property prediction tasks and assesses over 150 model‑task combinations. The study shows that current models, including chemical foundation models, struggle to generalize OOD, with the best model still exhibiting three times higher error than in‑distribution predictions.
arXiv:2606. 00401v1 Announce Type: cross Abstract: Simulating large molecular systems comprising thousands of atoms requires highly scalable methodologies.
arXiv:2606. 30170v1 Announce Type: cross Abstract: Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets.
arXiv:2602. 16908v2 Announce Type: replace-cross Abstract: Allegro is a machine learning interatomic potential model designed to predict atomic properties in molecules using E(3) equivariant neural networks.