Machine Learning Interatomic Potential– tag –
-
ArXiv Unveils ‘CrystalGRPO’: A Target-Aligned Reinforcement Learning Framework for Flow-Based Crystal Structure Prediction
arXiv International Overview The paper "CrystalGRPO" introduces a target-aligned and coverage-preserving reinforcement learning framework for flow-based generative crystal structure prediction (CSP). This framework combines MACE predicte... -
Matlantis Webinar Accelerates Computational Materials Design with Integrated CALPHAD, DFT, MLIPs, and AI Agents
Matlantis Japan Overview Matlantis offers an on-demand webinar accelerating computational materials design by integrating CALPHAD, Density Functional Theory (DFT), Machine Learning Interatomic Potentials (MLIPs), and AI-assisted simulati... -
EE Times: AI Adoption in Materials R&D Hinges More on People Than Technology, Toyota Example Highlights Accelerated Development
EE Times USA Overview EE Times argues that AI adoption in materials R&D increasingly depends on people and organizational factors rather than technological capabilities, as neural network potentials now offer DFT-comparable accuracy ... -
Massive Discovery of 9,139 Low-Dimensional Materials from Materials Project via Universal Computational Strategy, Including 887 Exfoliable 2D Materials
ACS Chemistry of Materials USA Overview This research combined universal machine learning interatomic potentials (UMLIPs) with an advanced force constant (FC)-based dimensionality classification method to massively discover new low-dimen... -
Transferable Machine Learning Interatomic Potential Accurately Predicts Thermodynamics, Structure, and Dynamics of Entangled Polymers from Oligomer Training
arXiv USA Overview This paper investigates machine learning interatomic potential (MLIP) development for polymers, identifying Atomic Cluster Expansion (ACE) as the most effective descriptor for polyethylene. It demonstrates that ACE pot... -
ACS Materials Au Publishes Comprehensive Tutorial on Machine Learning Tools for Electrocatalysis Simulations
ACS Materials Au USA Overview ACS Materials Au has released a tutorial on machine learning tools for electrocatalysis simulations, showcasing instruments like ML exchange-correlation functionals, Gaussian process optimizers, and ML inter... -
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... -
Atomic Representations from Pretrained MLIPs Prove Effective for Materials Generative Model Evaluation
arXiv USA Overview This paper demonstrates that atomic average features derived from pretrained machine learning interatomic potentials (MLIPs) like MACE are effective for evaluating the outputs of materials generative models. The resear... -
AI-Driven Battery Chemistry Simulators Evaluated for Adversarial Robustness: Output Validity vs. Chemical Sensitivity
OpenReview USA Overview The first systematic evaluation of adversarial robustness for AI-powered battery chemistry simulators, including MLIPs like MACE-MP-0 and CHGNet, revealed that physically constrained models maintain 90-92% physica... -
Quantum Machine Learning Interatomic Potential Achieves Enhanced Molecular Energy Prediction with Variational Quantum Algorithm
arXiv USA Overview This study applied quantum circuit learning to machine learning interatomic potentials (MLIPs), improving molecular dataset energy predictions. Using a quantum transfer learning architecture, the ANI model was retraine...
