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.
By Danish Khan, Maurice D. Hanisch, Nikolai Argatoff, Evan Xie, Sandeep Sharma, Anima Anandkumar
The paper introduces Gaussian Splatting for Density Functional Theory (GS‑DFT), a method that represents molecular orbitals as a cloud of Gaussians optimized via gradient descent. GS‑DFT replaces fixed atom‑centered basis sets with an adaptive, differentiable orthogonalization and efficient two‑electron integral evaluation, achieving accuracy comparable to large conventional bases with far fewer parameters. The solver scales quadratically with cloud size, enabling simulations of up to 2,742 atoms on a single four‑GPU node at triple‑zeta precision.
By Andr\'es Guzm\'an-Cordero, Cindy Zhang, Majdi Hassan, Marta Skreta, Kirill Neklyudov, Matija Medvidovi\'c
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.
By Beom Seok Kang, Vignesh C. Bhethanabotla, Amin Tavakoli, Maurice D. Hanisch, Arimitsu Horikawa-Strakovsky, Miguel Nouman, Danish Khan, William A. Goddard III, Anima Anandkumar
arXiv:2608. 03260v1 Announce Type: new Abstract: Pretraining has shown strong potential for learning transferable representations, yet it remains underexplored for electron-density-based molecular learning.
By Liang Shuang, Haocheng Wang, Jiayi Song, Shuquan Ye, Ben Fei
arXiv:2606. 30961v1 Announce Type: cross Abstract: Advances in deep learning architectures and representations have enabled ML-driven chemical property prediction, but state-of-the-art (SOTA) models have remained largely confined to independent codebases and lack support for diverse chemical species.
By Jacob W. Toney, Samir Darouich, Yiran Wang, Aaron G. Garrison, Johannes K\"astner, Heather J. Kulik
arXiv:2606. 00794v1 Announce Type: cross Abstract: Merging first-principles calculations with machine learning (ML), we aim to accelerate the exploration of catalytic behaviour in novel materials.
By Pavlo Melnyk, Anmar Karmush, M{\aa}rten Wadenb\"ack, Ania Beatriz Rodr\'iguez-Barrera, Johanna Rosen, Michael Felsberg, Jonas Bj\"ork
arXiv:2503. 19847v2 Announce Type: replace-cross Abstract: The accurate quantum chemical calculation of excited states is a challenging task, often requiring computationally demanding methods.
By Zeno Sch\"atzle, P. Bern\'at Szab\'o, Alice Cuzzocrea, Mat\v{e}j Mezera, Frank No\'e
The paper introduces MEHnet-MG, an equivariant neural network that predicts a one‑electron Hamiltonian from a single inexpensive B3LYP/def2‑SVP calculation and uses it to compute a wide range of molecular properties—energy, optical gap, dipole, quadrupole, polarizability, Mulliken charges, and Mayer bond orders—at coupled‑cluster accuracy for nine main‑group elements, including phosphorus, sulfur, and chlorine. Trained on a new CCSD(T) dataset, the model reduces property errors by factors ranging from 3.8 to 230 compared to various DFT methods while adding only ~25 ms per molecule. Importantly, by deriving properties from a predicted Hamiltonian rather than pooling atomic features, the architecture naturally incorporates correct size‑scaling, enabling accurate extrapolation to large π‑conjugated systems (up to 58 atoms) where traditional pooling‑based models fail.
By Wenhao He, Xu Chen, Noah Song, Haowei Xu, Tim S. Hindges, Bohan Li, Zihan Lin, Yu Yao, Avetik R. Harutyunyan, Fang Liu, Yao Wang, Hao Tang, Ju Li
The paper presents a hierarchical deep‑learning framework that integrates compositional, structural, and transport models to screen solid‑state electrolytes. Four modules—L‑G‑DCNN, DenseGNN, MatterSim, and DeePMD—coordinate to evaluate thermodynamics, multi‑property performance, and kinetic transport, outperforming existing methods. Applied to over 30 million candidates, the workflow identifies 97 high‑performance materials, mainly halides, and links Li⁺ jump‑network connectivity to ionic conductivity while highlighting limits for oxide electrolytes.
By Hongwei Du, Dingyang Lv, Baole Wei, Yongheng Li, Feng Yu, Ziheng Lu, Siqi Shi, Hong Wang
arXiv:2603. 14700v2 Announce Type: replace-cross Abstract: Machine learning interatomic potentials (MLIPs) have become widely used tools in atomistic simulations.
By William J. Baldwin, Ilyes Batatia, Martin Vondr\'ak, Johannes T. Margraf, G\'abor Cs\'anyi
arXiv:2607. 05736v1 Announce Type: new Abstract: Molecular property prediction often relies on isolated data modalities, where continuous 3D graph neural networks (GNNs) struggle to efficiently capture long-range topological dependencies and exact macroscopic heuristics.
By Qiwei Han, Chi Zhou, Ruobing Wang, Zheng Ma
arXiv:2607. 25597v1 Announce Type: new Abstract: The reactivity of lithium-metal electrolytes arises from the interplay of molecular functional groups, Li$^+$ solvation, and salt-anion participation.
By Mingkang Liu, Huize Yu, Yanbin Gao, Nan Yao, Xiang Chen, Lei Shen