Tag
A novel AI model using a Fourier neural operator variant enables density functional theory to scale nearly linearly with system size, allowing efficient simulations of large quantum systems like a magnesium dislocation with 80k electrons on a single GPU.
MALOQ introduces a massively accelerated machine learning model for predicting density functional theory Hamiltonian/density matrices, enabling electronic-structure calculations for systems with up to 100k atoms using an SO(2)-equivariant backbone and scalable graph distribution, achieving over 30% time-per-epoch reduction on the Alps supercomputer.
This ICML 2026 paper introduces Derivative Informed XC-Loss (DI-Loss), a training approach for machine-learned exchange-correlation functionals that incorporates first and second derivative supervision on the Grassmannian of density matrices. Across four architectures, DI-Loss reduces total-energy MAE by 66% compared to energy and density supervision alone, and improves excited-state predictions in TDDFT calculations.
This paper presents an agentic system using Large Language Models to automate the discovery of exchange-correlation functionals in Density Functional Theory, achieving improvements over human-designed baselines while highlighting challenges with benchmark overfitting.