Hugging Face Trending Papers
Beyond DFT electronic band structures via dual-space orbital learning
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Oct 15
Beyond DFT electronic band structures via dual-space orbital learning
arXiv:2610.19919v1 Announce Type: new Abstract: Accurate electronic band structures are essential for predicting material properties, but high-fidelity calculations are computationally demanding. We...
arXiv AI
Aug 26
Learning the Kohn-Sham map with neural operators for quasi-linear scaling density functional theory
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.
arXiv AI
Jun 9
Agentic multi-fidelity learning of quasiparticle and excitonic properties
arXiv:2606. 07836v1 Announce Type: cross Abstract: Many-body GW-Bethe-Salpeter equation calculations are essential for accurate simulations of electronic structure and optical properties in modern low-dimensional nanomaterials.
arXiv AI
6d ago
Where the Error Lives: Spectral Representations of Learned Kohn-Sham Hamiltonians
The paper investigates how small entry‑wise errors in machine‑learned Kohn‑Sham Hamiltonians can still lead to inaccurate eigenvalues and eigenvectors. It shows that existing physics‑informed losses only partially capture the error, and proposes using the cumulative local density of states (cumulative LDOS) as a complete training signal that uniquely determines the Hamiltonian. Fine‑tuning three Hamiltonian networks with this loss, called FermiScope, reduces HOMO‑LUMO gap errors without increasing element‑wise error, and the improvement generalizes to out‑of‑distribution and molecular‑dynamics scenarios.
arXiv AI
Oct 28
Physical structure as an organizing principle for universal Hamiltonian learning
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.
arXiv Machine Learning
Oct 19
Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs
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.