Molecular Dynamics– tag –
-
Deletion Method Outperforms Generative AI Approaches for Extracting Atomic Environments in MLIP-Driven MD Simulations
arXiv USA Overview A systematic analysis of optimal methods for extracting small atomic environments suitable for DFT calculations from large structures, a challenge in applying machine learning interatomic potentials (MLIPs) to large-sc... -
AI-Powered Simulations Unlock Next-Gen Battery Design: How MLIPs Bridge the Gap Between DFT and Classical MD
ResearchGate Overview A recent review highlights how Machine Learning Interatomic Potentials (MLIPs) are effectively addressing persistent challenges in computational materials science for battery development. By bridging the gap between... -
Computational Powerhouse: AI and DFT Drive Next-Gen Sodium-Ion Battery Innovation
MDPI Overview A new MDPI review highlights the critical role of theoretical calculations, including Density Functional Theory (DFT) and Molecular Dynamics (MD), alongside Machine Learning (ML), in accelerating the discovery and optimizat... -
Iterative Fine-Tuning Strategy for Universal Machine Learning Interatomic Potentials (uMLIPs) Yields Stable, High-Accuracy Models for Out-of-Domain Tasks
PubMed Overview Research on universal machine learning interatomic potentials (uMLIPs) demonstrates that "iterative fine-tuning" effectively generates stable molecular dynamics simulations and high-accuracy models for out-of-domain tasks... -
Unlocking Precision: Iterative Fine-Tuning Overcomes Bias in Universal MLIPs for Enhanced Material Simulations
Unknown Source Unknown Overview Universal Machine Learning Interatomic Potentials (uMLIPs) promise broad applicability across the periodic table, yet accurate out-of-domain predictions demand specialized fine-tuning. This study reveals t... -
Meta FAIR and Stanford Researchers Successfully Fine-Tune UMA Model for High-Precision Simulation of WS2 Oxygen Plasma Interactions
arXiv USA Overview Researchers from Meta FAIR and Stanford University successfully fine-tuned the UMA universal machine-learned interatomic potential (MLIP) model specifically for oxygen plasma interactions with WS2. This study addresses... -
LLNL Pioneers New Electrolyte Design for Sodium and Lithium Batteries, Boosting Performance and Thermal Stability with AI and Molecular Simulations
Commonwealth Union USA Overview Scientists at Lawrence Livermore National Laboratory (LLNL) have integrated molecular dynamics simulations with physics-informed machine learning to yield groundbreaking insights into electrolyte design fo... -
UNCC Research Group Develops ‘PyXtal_FF’ for ML Interatomic Potential Generation, Dramatically Reducing Computational Cost of Atomic Simulations
University of North Carolina at Charlotte USA Overview Researchers at the University of North Carolina at Charlotte (UNCC) have developed 'PyXtal_FF,' a package for generating Machine Learning Interatomic Potentials (MLIAP). MLIAPs enabl... -
GPUMD 4.0 Achieves High-Performance Versatile Materials Simulations with Integrated Machine-Learned Potentials
Materials Genome Engineering Advances Global Overview The high-performance molecular dynamics package GPUMD 4.0 has been released, integrating advanced machine-learning potentials (MLPs) based on the NeuroEvolution Potential (NEP) framew... -
arXiv: New ‘ATR’ Framework Enhances Dynamic Stability of MLIPs by Actively Rejecting Pseudo-Labels
arXiv Global Overview A new arXiv preprint introduces the 'Adaptive Multi-Teacher Routing (ATR)' framework, which significantly improves the reliability and generalization capability of universal machine-learning interatomic potentials (...
