Crystal– tag –
-
Tokyo University of Science Unveils AI-Driven Inverse Design for High-Speed Spin Wave Computing
EurekAlert! Japan Overview Researchers at Tokyo University of Science have developed an AI-driven inverse design framework, integrating genetic algorithms with micromagnetic simulations, to optimize magnonic crystal (MC) structures. This... -
Northwestern University Accelerates Electronic and Energy Material Design with Property-Predicting Machine Learning Model ‘LVGP’
Northwestern University (Paula M. Trienens Institute For Sustainability And Energy) USA Overview Northwestern University's Wei Chen research group developed the Latent Variable Gaussian Process (LVGP) machine learning model, which conver... -
Energy-Constrained MLIP Embedding Improves Prediction Accuracy for Hydrogen Evolution Electrocatalysts
ACS Publications (Journal of Chemical Information and Modeling) Overview Researchers developed an "energy-constrained" machine learning framework integrating MLIP-derived energy descriptors with pre-trained Crystal Hamiltonian Graph Neur... -
Machine Learning Transforms Materials Science: From Property Prediction to Structural Design, Emphasizing LLM Validation
Academic Review / Journal Global Overview A new academic review highlights the transformative role of machine learning (ML) in materials science, detailing its impact on property prediction, novel material discovery, and process optimiza... -
ACS Publications Proposes Physics-Driven Computational Paradigm with AI-Assisted Multiscale Simulation for Low-Temperature Flexible Organic Crystals
ACS Publications USA Overview This research proposes a physics-driven computational paradigm for elucidating the properties of low-temperature flexible organic crystals. Combining AI-assisted multiscale simulation and machine-learning fo... -
arXiv Paper: Model-Agnostic Graph Prompt Learning Significantly Enhances GNN Crystal Property Prediction Accuracy
arXiv International Overview This paper proposes a novel model-agnostic soft prompt learning framework to improve the crystal property prediction performance of Graph Neural Networks (GNNs). By incorporating node-level and graph-level so... -
GitHub Repository ‘awesome-ai-for-science’ Launched, Featuring Google GNoME, Microsoft MatterGen, and Other Curated AI Tools Accelerating Scientific Discovery
GitHub (ai-boost) International Overview The 'awesome-ai-for-science' repository has been launched on GitHub, providing a curated list of AI tools and frameworks that accelerate discovery across diverse scientific fields, including physi... -
arXiv Paper: SciReasoner Boosts Multi-Modal Structural Reasoning for Proteins, Molecules, and Crystals with Enhanced Accuracy
arXiv International Overview SciReasoner has been introduced as an innovative multi-modal scientific foundation model enabling structural reasoning for proteins, molecules, and crystals. By discretizing structural elements into a unified... -
Comprehensive Review Details Machine Learning’s Role in Materials Science, From GNNs to LLMs for Data-Driven Discovery
Nature Computational Materials International Overview A new review paper offers a comprehensive analysis of machine learning's advancements in data-driven discovery and functional applications within materials science. Key technologies l... -
Foundation Models Uncover Novel High-Pressure Phase Ca6FeNi, Revolutionizing Materials Discovery Workflow
arXiv USA Overview A recent preprint on arXiv introduces a self-consistent foundation model-assisted crystal structure prediction (CSP) workflow that integrates evolutionary search with adaptive data selection and fine-tuning. This innov...
