Meta FAIR releases large inorganic materials dataset and AI models

Meta FAIR has released the Open Materials 2024 (OMat24) dataset, comprising over 110 million density functional theory calculations for inorganic materials. This release also includes accompanying pre-trained EquiformerV2 models, which have achieved state-of-the-art performance on the Matbench Discovery leaderboard. These models can predict ground-state stability and formation energies with high accuracy, aiming to accelerate AI-driven materials discovery. AI

IMPACT Accelerates AI-driven materials discovery by providing a large open dataset and high-performing models for predicting material properties.

RANK_REASON The cluster describes the release of a new dataset and accompanying AI models for materials science research, published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• density functional theory
• EquiformerV2
• Matbench Discovery leaderboard
• Meta FAIR
• Open Materials 2024 (OMat24)

• paper
• product
• infra

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