Microsoft Research has released Skala 1.1, an updated version of its deep-learning density functional theory (DFT) approach. This new version is trained on 2.5 times more data than its predecessor, leading to significantly improved accuracy in molecular simulations for thermochemistry, reaction kinetics, and structure prediction. To enhance accessibility, Skala is now integrated into several widely used computational chemistry codes, including CP2K, Psi4, FHI-aims, ORCA, and VASP. Microsoft Research is also launching a living benchmark to track the performance of future Skala releases and accelerate progress in predictive computational chemistry. AI
IMPACT Enhances predictive capabilities in computational chemistry, potentially accelerating discovery in materials science and drug development.
RANK_REASON Release of an updated scientific model and its integration into existing software tools. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
