A differentiable pipeline uses continuous atom occupancy and gradient descent plus a neural network to optimize short-range order in multi-element alloys directly for target stiffness properties.
Musaelian , author S
11 Pith papers cite this work, alongside 556 external citations. Polarity classification is still indexing.
11
Pith papers citing it
556
external citations · Crossref
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
A protocol is introduced to derive effective inertial and viscous-damping constants for nonequilibrium polarization dynamics in soft-mode ferroelectric PbTiO3.
SOAP and SOAP-Muon optimizers deliver faster convergence and higher final accuracy than Adam for NequIP and Allegro MLIPs, with the largest gains under partial force supervision.
Subsurface vacancies are thermodynamically preferred over surface vacancies on specific FCC and HCP metal surfaces due to a geometry-electronic decoupling mechanism identified via DFT and ML force fields.
Molecular dynamics simulations find that both I and MA defects in MAPbI3 diffuse rapidly at room temperature with barriers of 0.15-0.20 eV, with MA interstitials moving via concerted mechanisms and no MA vacancy migration observed.
Bayesian active learning with SSCHA predicts phase transitions in materials like CsPbI3 using only 50-256 first-principles calculations.
A 1.62-trillion-atom molecular dynamics simulation achieves ab initio accuracy with 100x speedup over prior machine learning force fields and 86.9% weak scaling to 45,000 GPGPUs.
QCOF ML potentials tuned on COF data outperform general MACE models for defective systems and reveal higher thermal defect sensitivity in CTF-1 versus COF-LZU1 with nearly invariant low-strain mechanics.
Introduces torch-pme and jax-pme libraries that embed Ewald-based long-range methods and purified descriptors into atomistic ML for accurate handling of non-local physical interactions.
An agentic HPC skill automates NEB microkinetics, recovers from common failures, and benchmarks ~12 universal MLIPs against DFT for CO2 sublimation on graphite.
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.
citing papers explorer
-
Differentiable inverse design of short-range order in high-entropy alloys: from target sro to target property
A differentiable pipeline uses continuous atom occupancy and gradient descent plus a neural network to optimize short-range order in multi-element alloys directly for target stiffness properties.
-
Effective dynamic constants for nonequilibrium third-principles simulations
A protocol is introduced to derive effective inertial and viscous-damping constants for nonequilibrium polarization dynamics in soft-mode ferroelectric PbTiO3.
-
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
SOAP and SOAP-Muon optimizers deliver faster convergence and higher final accuracy than Adam for NequIP and Allegro MLIPs, with the largest gains under partial force supervision.
-
Anomalous Subsurface Vacancy Stabilization Dictated by Geometry-Electronic Decoupling on Metal Surfaces
Subsurface vacancies are thermodynamically preferred over surface vacancies on specific FCC and HCP metal surfaces due to a geometry-electronic decoupling mechanism identified via DFT and ML force fields.
-
A Unified microscopic picture of cation and anion migration in MAPbI$_3$
Molecular dynamics simulations find that both I and MA defects in MAPbI3 diffuse rapidly at room temperature with barriers of 0.15-0.20 eV, with MA interstitials moving via concerted mechanisms and no MA vacancy migration observed.
-
Predicting challenging phase transitions with Bayesian active learning
Bayesian active learning with SSCHA predicts phase transitions in materials like CsPbI3 using only 50-256 first-principles calculations.
-
Trillion-atom molecular dynamics simulations with ab initio accuracy
A 1.62-trillion-atom molecular dynamics simulation achieves ab initio accuracy with 100x speedup over prior machine learning force fields and 86.9% weak scaling to 45,000 GPGPUs.
-
Data-Driven Thermal and Mechanical Modeling of Defective Covalent Organic Frameworks
QCOF ML potentials tuned on COF data outperform general MACE models for defective systems and reveal higher thermal defect sensitivity in CTF-1 versus COF-LZU1 with nearly invariant low-strain mechanics.
-
Fast and flexible long-range models for atomistic machine learning
Introduces torch-pme and jax-pme libraries that embed Ewald-based long-range methods and purified descriptors into atomistic ML for accurate handling of non-local physical interactions.
-
Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery
An agentic HPC skill automates NEB microkinetics, recovers from common failures, and benchmarks ~12 universal MLIPs against DFT for CO2 sublimation on graphite.
-
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.