New MALOQ model accelerates quantum transport calculations with ML

Researchers have developed MALOQ, a new machine learning model designed to accelerate the prediction of electronic-structure matrices for quantum transport calculations. This model, built on an SO(2)-equivariant architecture, can handle systems ranging from a few to 100,000 atoms and large basis sets. MALOQ significantly reduces computation time, achieving over a 30% reduction in training time per epoch compared to previous methods and enabling inference on arbitrarily large material graphs. AI

IMPACT This model could enable larger-scale simulations in materials science and quantum physics, potentially accelerating discovery.

RANK_REASON The cluster contains a research paper detailing a new machine learning model and its technical specifications. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Alexandros Nikolaos Ziogas
• arXiv

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →