2026– date –
-
Causal-Aware Framework “ARIA” Enhances LLM Reliability in 2D Material Design by Integrating Causal Reasoning
arXiv Unknown Overview Addressing the challenge of generative models failing to satisfy physical causality in materials discovery, the ARIA framework extends large language models (LLMs) with causal reasoning. Utilizing knowledge graphs,... -
DeepMind’s GNoME and Microsoft’s MatterGen Drastically Accelerate AI-Driven Materials Discovery, Rapidly Screening Millions of Inorganic Crystals
AI CERTs News USA Overview Advanced AI pipelines like DeepMind's GNoME and Microsoft's MatterGen are leveraging graphene neural networks and machine learning potentials to screen millions of inorganic crystals at unprecedented speeds. Th... -
University of Washington Develops Self-Improving Design Loop for New Materials via AI-Quantum Computing Fusion
richardmitnick (blog) USA Overview University of Washington research has developed a self-improving design loop for new materials through the fusion of AI and quantum computing. AI simulates complex quantum behaviors in stacked atomic sh... -
MDPI Buildings Features Mechanically Constrained GNN for Enhanced Linear Static Analysis of Planar Frame Structures
MDPI Buildings Switzerland Overview This study developed a mechanically constrained Graph Neural Network (GNN) method for 2D linear elastic static analysis of planar truss and building frame structures. The method represents structural s... -
Japan Times Reports on ‘Physical AI’ Focus: Japan’s Manufacturing Data to Enable Robots to Autonomously Support Human Workers with High Precision
The Japan Times Japan Overview The Japan Times reported on Japan's focus to advance 'physical AI,' systems enabling robots to autonomously support human workers with high precision, by leveraging its manufacturing data. Driven by governm... -
Oxford Academic: Machine Learning and LLM Synergy Uncovers High-Entropy Alloy Electrocatalytic Activity, Enabling High-Throughput Discovery
National Science Review (Oxford Academic) China Overview Research published in Oxford Academic combined machine learning (including GNNs) with an LLM-driven collaborative framework to unveil correlations between high-entropy alloy (HEA) ... -
OAE Publishing Reveals Interpretable Machine Learning Deciphers Strength-Ductility Trade-off in (CuNiMn)-X Alloys, Streamlining High-Performance Copper Alloy Design
OAE Publishing Inc. China Overview OAE Publishing Inc. has presented an integrated strategy utilizing interpretable machine learning to decipher the strength-ductility trade-off in (CuNiMn)-X alloys, enabling efficient design of high-per... -
arXiv Paper Presents ML Model for High-Precision Prediction of Metallic Glass Critical Cooling Rates Using Elemental and Molecular Simulation Features
arXiv USA Overview This study presents a machine learning model for predicting critical cooling rates of metallic glasses using computationally derived properties, specifically elemental and molecular dynamics simulation-based features. ... -
D-Wave Develops Gate-Model Quantum Computing Platform, Expanding R&D Scope in Quantum Chemistry and Materials Science
D-Wave Canada Overview D-Wave is advancing its gate-model quantum computing platform to expand the range of problems organizations can explore, including quantum chemistry, molecular R&D, materials, catalysts, and energy systems. The... -
SES AI Unveils ‘Molecular Universe’ AI Science SaaS Platform, Validated by NVIDIA to Accelerate Battery Material Discovery
Stock Pursuit USA Overview SES AI has launched its 'Molecular Universe' AI Science SaaS platform, mapping a database of over 200 million small molecules to accelerate battery electrolyte material discovery. Validated by NVIDIA, this plat...
