7 papers
DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution
Tiancheng Li, Wentao Li, Anyang Peng +4
Machine-learning interatomic potentials now approach quantum-mechanical accuracy, but the most expressive equivariant architectures are costly to evaluate, and the leading ones dep…
Mixture of experts architectures for machine learning interatomic potentials
Yuzhi Liu, Duo Zhang, Anyang Peng +3
Machine Learning Interatomic Potentials (MLIPs) enable accurate large-scale atomistic simulations, yet improving their expressive capacity efficiently remains challenging. Here we…
A Graph Neural Network for the Era of Large Atomistic Models
Duo Zhang, Anyang Peng, Chun Cai +11
Foundation models, or large atomistic models (LAMs), aim to universally represent the ground-state potential energy surface (PES) of atomistic systems as defined by density functio…
Multi-Task Fine-Tuning Enables Robust Out-of-Distribution Generalization in Atomistic Models
Chengqian Zhang, Duo Zhang, Anyang Peng +7
Accurate de novo molecular and materials design requires structure-property models that generalize beyond known regimes. Although pretrained atomistic models achieve strong in-dist…
LAMBench: A Benchmark for Large Atomistic Models
Anyang Peng, Chun Cai, Mingyu Guo +9
Large Atomistic Models (LAMs) have undergone remarkable progress recently, emerging as universal or fundamental representations of the potential energy surface defined by the first…
DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
Jinzhe Zeng, Duo Zhang, Anyang Peng +44
In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for m…