September 2026– date –
-
Machine Learning Revolutionizes Magnetic Functional Alloy Design: Generative GNNs and High-Throughput DFT Discover 2D Magnets
AIP Advances USA Overview This article details recent advancements in the design of magnetic functional alloys (MFAs) leveraging machine learning (ML), highlighting how ML has contributed to the design of magnetocaloric, magnetostrictive... -
Oak Ridge National Lab’s AI-Guided System Autonomously Arranges Molecules to Build Functional Materials, Expanding Electronic and Quantum Material Possibilities
Facebook (Oak Ridge National Laboratory) USA Overview Oak Ridge National Laboratory announced an AI-guided system that autonomously arranges individual molecules to construct functional materials. This technology, where AI guides an ultr... -
Berkeley Lab Revolutionizes Solid Electrolyte Design with Hybrid ML and Experimental Data, Discovering Ion Transport Dominated by Dissociation Mechanisms, Not Viscosity
Facebook (Berkeley Lab Energy Storage Center) USA Overview A Berkeley Lab team adopted a hybrid machine learning approach combining experimental data and computational descriptors, revealing that ion transport in ionic liquids is primari... -
SES AI’s ‘Molecular Universe’ Platform Accelerates Drone Battery Development by Years, Identifies Optimal Materials from 100 Million Molecules in Weeks
UST USA Overview UST reports SES AI is revolutionizing battery development by applying AI to efficiently identify materials with specific application requirements. Their 'Molecular Universe' platform maps approximately 100 million potent... -
SandboxAQ’s AQCat AI Model on Claude Science Accelerates Catalyst Screening 20,000x, Considers Magnetic Behavior, Trained on High-Fidelity Data
Quantum Zeitgeist USA Overview SandboxAQ has released AQCat, an AI model running on Claude Science, capable of accelerating potential catalyst screening by up to 20,000 times faster than traditional lab methods. AQCat predicts catalyst e... -
Texas A&M Receives $24.9M Grant for Autonomous Robotic Metallurgist Materials Innovation Platform (ARM-MIP): Robots and AI to Test, Analyze New Alloys 24/7
Facebook (Texas A&M University) USA Overview Texas A&M University secured a $24.9 million grant to establish the Autonomous Robotic Metallurgist Materials Innovation Platform (ARM-MIP), an autonomous metal discovery lab. This state-o... -
ACS Publications: PolyCLIP Framework Outperforms Existing Polymer Property Prediction Models by 13.32%, Establishes New Foundation for Multimodal Polymer Informatics
ACS Publications USA Overview ACS Publications announced PolyCLIP, a CLIP-based multimodal framework, achieved up to 13.32% better performance in polymer property prediction than existing unimodal and multimodal models. The study demonst... -
LLNL Optimizes Photoelectrochemical Devices via Hybrid DFT Simulations and AI, Diagnosing Point Defect Effects, Doping, and Alloying for Performance Enhancement
Lawrence Livermore National Laboratory (LLNL) USA Overview Lawrence Livermore National Laboratory (LLNL) has significantly advanced photoelectrochemical (PEC) device optimization by integrating advanced hybrid density functional theory (... -
Ansys: Inverse Design Revolutionizes Materials R&D, Automating Design from Desired Performance to Drastically Cut Time and Cost
Ansys USA Overview Ansys details how inverse design, a computational approach, reverses traditional trial-and-error, automating material design from desired specifications. Powered by machine learning and deep learning optimization, this... -
MIT’s CrysVCD Framework Significantly Boosts AI Material Design Stability, Slashes Computational Costs, Accelerating Practical Material Development
Silicon Semiconductor News USA Overview MIT researchers have developed 'CrysVCD,' an AI framework that significantly enhances the chemical stability of generated materials while achieving target properties, applied early in the design pr...
