Orb模型比现有通用势函数快3-6倍，误差降低31%。
Orb: A Fast, Scalable Neural Network Potential
- 基于扩散预训练构建通用原子势函数
- 在Matbench基准上误差减少31%，速度提升3-6倍
- 适合材料结构优化与分子动力学模拟
我们提出Orb，一类通用的原子间势函数，用于材料的原子级建模。Orb模型的速度比现有通用势函数快3至6倍，在多种分布外材料的模拟中表现稳定；发布时，在Matbench Discovery基准上相比其他方法误差降低了31%。研究探索了材料领域基础模型开发的多个方面，重点聚焦于扩散预训练。评估了Orb在几何优化、蒙特卡洛和分子动力学模拟中的应用性能。
原文摘要 · Abstract (English)
We introduce Orb, a family of universal interatomic potentials for atomistic modelling of materials. Orb models are 3-6 times faster than existing universal potentials, stable under simulation for a range of out of distribution materials and, upon release, represented a 31% reduction in error over other methods on the Matbench Discovery benchmark. We explore several aspects of foundation model development for materials, with a focus on diffusion pretraining. We evaluate Orb as a model for geometry optimization, Monte Carlo and molecular dynamics simulations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。