aiqbench takeMachine Learning

Microsoft Research's Skala 1.1 advances density functional theory by leveraging a significantly expanded and diverse training dataset to surpass hybrid functionals in accuracy while retaining computational efficiency. This development represents a critical step toward scalable, predictive frameworks for molecular simulation that can be directly integrated into major quantum chemistry codes like CP2K and VASP.

Sources coveringQuantum Zeitgeist, LessWrong, Latent Space, SiliconANGLE

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Microsoft Research’s Skala 1.1 boosts DFT accuracy with 2.5x more training data

Quantum ZeitgeistAugust 24, 20263 min read

Skala 1.1, trained on 2.5× more data than its predecessor, delivers substantially higher accuracy across key molecular simulation challenges, including thermochemistry, reaction kinetics, and molecular structure prediction. Skala is now available in CP2K and is being integrated into Psi4, FHI-aims, ORCA and VASP.

Microsoft Research has broadened access to Skala 1.1, a deep-learning approach to density functional theory (DFT), after training the updated model on 2.5 times more data than its predecessor. This increased dataset delivers improvements across crucial molecular simulation challenges like thermochemistry, reaction kinetics, and molecular structure prediction. Skala is now available within the CP2K code, with integration planned for Psi4, FHI-aims, ORCA and…

Excerpt shown under the publisher's RSS terms · 63 words · full text and figures are on the publisher's site

Read at Quantum Zeitgeist ↗Ask about this article