arXiv:2610.19630v1 Announce Type: cross Abstract: Automated materials discovery requires evaluating large pools of candidate configurations, with density functional theory (DFT) as a major throughput...
arXiv:2607. 14486v1 Announce Type: cross Abstract: Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows.
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 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 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."
The paper explores multivariate conformal uncertainty propagation for multitask atomistic simulations, introducing methods such as Bonferroni‑corrected hyperrectangles, hyperellipsoidal sets based on Mahalanobis distance, and custom loss functions within conformal risk control. It applies these techniques to calibrate predictions of energies, forces, and stresses, then propagates the resulting uncertainty sets to downstream quantities like elastic constants and vacancy formation energies. The study emphasizes how incorporating correlation predictions can capture symmetries and error cancellation, and discusses the interaction between computational protocols and conformal guarantees.
arXiv:2610.06985v2 Announce Type: replace-cross Abstract: Atomistic foundation models screen hypothetical crystals by thresholding predicted energies, an output that states neither how likely a candi...
arXiv:2508. 02641v2 Announce Type: replace-cross Abstract: Molecular crystal structure prediction (CSP) is essential for applications in pharmaceuticals and organic electronics.
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. 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.
arXiv:2606. 15217v1 Announce Type: cross Abstract: Offline model-based optimization (MBO) proposes candidates by optimizing a surrogate trained on a fixed historical dataset.
The paper presents a neural operator that learns the Kohn–Sham map, directly predicting electron density from the Kohn–Sham potential without orbital diagonalization. Using a domain‑invariant SE(3)‑equivariant Fourier neural operator trained on 8,504 molecules and solids, the model achieves quasi‑linear scaling self‑consistent field (SCF) convergence across diverse systems—including organic molecules, insulators, and metals—while reproducing Kohn–Sham DFT accuracy for densities, spectra, and structural observables. This enables large‑scale simulations, such as magnesium dislocation densities with 82,500 valence electrons, on a single GPU.