Distilling universal machine-learning potentials for moir'e lattices across one million atoms
cond-mat.mtrl-sci, cond-mat.mes-hall
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- Fine-Tuned Machine-Learned Interatomic Potentials for Structural and Vibrational Properties of Twisted 2D Materials
- Orb-v3: atomistic simulation at scale
- Fast and Accurate Foundation Models for Equivariant Machine-Learned Interatomic Potentials
- Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
- Distillation of atomistic foundation models across architectures and chemical domains
- EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
Related papers
- Mode-selective electron-phonon coupling drives charge density waves in the kagome metals YRu 3 Si 2 and LaRu 3 Si 2
- Restoring the Surface Magnetic Gap in MnBi 2 Te 4
- ATLAS: A Foundation Neural Sampler for Amorphous Materials
- A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics
- Nonlinear dynamics in magnonic Fabry-P' e rot resonators: Low-power neuron-like activation and transmission suppression
- AES-Debye: an Accurate, Efficient, and Scalable Engine for Debye Scattering Calculations