Research
Microsoft's Skala 1.1 Enhances DFT Accuracy
Microsoft Researchhigh confidence
Why it matters
- →Skala 1.1 improves DFT accuracy, crucial for precise molecular simulations.
- →Integration into major software packages broadens accessibility for researchers.
- →Continuous improvement model ensures Skala remains at the forefront of DFT advancements.
Microsoft Research has released Skala 1.1, an updated version of its deep-learning approach to density functional theory (DFT). This version is trained on 2.5 times more data, significantly improving accuracy in molecular simulations. Skala is now integrated into major software packages like CP2K and is being added to others such as Psi4 and VASP. These integrations aim to make advanced DFT capabilities more accessible to scientists, enhancing the predictive power of computational chemistry across various fields.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Microsoft's MatterSim Advances Materials AI
Microsoft Research · May 12, 2026 · Background
