Orb: A Fast, Scalable Neural Network Potential
This work addresses the need for efficient and accurate materials modeling, though it appears incremental as it builds on existing potential methods with specific improvements.
The authors tackled the problem of slow and inaccurate universal interatomic potentials for atomistic modeling by introducing Orb, which is 3-6 times faster than existing methods and achieved a 31% reduction in error on the Matbench Discovery benchmark.
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.