SE(3)-equivariant transformer proxies of environment-similarity order parameters enable metadynamics free energy calculations for colloidal crystals, predicting that surface potential redistribution stabilizes CsCl versus Th3P4 structures.
TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations
3 Pith papers cite this work, alongside 51 external citations. Polarity classification is still indexing.
3
Pith papers citing it
51
external citations · Crossref
years
2026 3representative citing papers
GROMACS now runs multi-GPU DeePMD inference for molecular dynamics, reaching 40-66% strong scaling efficiency up to 32 devices on a 15k-atom protein system with over 90% time in inference.
This perspective paper categorizes hybrid architectures for combining mechanistic and data-driven models using residual learning, Neural ODEs, and solver-in-the-loop to model neurological disorder progression.
citing papers explorer
-
Sampling Free Energy Landscapes of Ionic Colloidal Crystal Systems using Machine-Learned Proxy Collective Variables
SE(3)-equivariant transformer proxies of environment-similarity order parameters enable metadynamics free energy calculations for colloidal crystals, predicting that surface potential redistribution stabilizes CsCl versus Th3P4 structures.
-
Making Room for AI: Multi-GPU Molecular Dynamics with Deep Potentials in GROMACS
GROMACS now runs multi-GPU DeePMD inference for molecular dynamics, reaching 40-66% strong scaling efficiency up to 32 devices on a 15k-atom protein system with over 90% time in inference.
-
Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming
This perspective paper categorizes hybrid architectures for combining mechanistic and data-driven models using residual learning, Neural ODEs, and solver-in-the-loop to model neurological disorder progression.