Troy– Author –
-
LLM and MLIP Break Solid Electrolyte Discovery Bottlenecks, AI Closed-Loop Architecture Accelerates Development
arXiv Unknown Overview An innovative approach integrating large language models (LLMs) and machine learning potentials (MLIPs) is proposed to address bottlenecks in solid electrolyte discovery. A closed-loop architecture, combining AI-dr... -
AI-Physics Collaboration Achieves Breakthrough in Hydrogen Storage Material Design, Pinpointing Optimal Lattice Architectures
Phys.org USA Overview An innovative collaboration between AI and physics has yielded a breakthrough in hydrogen storage material design. Research revealed a strong correlation between hydrogen storage capacity and the atomic-scale geomet... -
NUS and University of Toronto Launch $10M ‘Materials Data Foundry’ to Accelerate AI Materials Discovery
AcademicJobs.com Singapore Overview National University of Singapore (NUS) and the University of Toronto Acceleration Consortium have launched a $10 million 'Materials Data Foundry,' an open autonomous platform combining AI and robotics.... -
NC State Develops ‘Flex-Cat’ Self-Driving Lab, Autonomously Discovering Catalysts for On-Demand Product Switching
North Carolina State University USA Overview Researchers at North Carolina State University have developed 'Flex-Cat,' a self-driving chemistry lab integrating robotics, high-pressure chemical reactors, automated analysis, and AI. This s... -
Atinary Technologies Demonstrates Catalyst Optimization and Enhanced Process Safety with AI-Driven Closed-Loop Experiments
Atinary Technologies USA Overview Atinary Technologies has demonstrated a fundamental transformation in R&D processes through closed-loop experiments in self-driving labs, integrating AI, robotics, and human scientific expertise. By ... -
DTU Unveils ‘Self-Driving Lab’: AI and Robotics Slash Materials Discovery from Decades to Days
Mirage News デンマーク Overview The Technical University of Denmark (DTU) has unveiled an innovative 'self-driving lab' where AI and robotic arms autonomously conduct chemical experiments, promising to compress new materials development ... -
Bias Identified in Universal Machine-Learned Interatomic Potentials; Iterative Fine-Tuning Improves Accuracy
Journal of Chemical Theory and Computation (ACS Publications) USA Overview This study thoroughly investigated intrinsic biases in universal machine-learned interatomic potentials (uMLIPs), such as MACE, and their impact on fine-tuning qu... -
Meta FAIR’s Universal MLIP ‘UMA’ Precisely Models Oxygen Plasma Interactions with 2D Materials, Advancing Semiconductor Manufacturing
arXiv Unknown Overview Meta FAIR's universal machine-learned interatomic potential (MLIP) model, UMA, has demonstrated highly accurate modeling of oxygen plasma interactions with tungsten disulfide (WS2), a 2D material, with performance ... -
Machine Learning Potentials Accelerate Quantum Chemistry by Up to 1 Million-Fold, Revolutionizing Materials Science
ACS Central Science USA Overview Rapid advancements in machine learning interatomic potentials (MLIPs) are poised to accelerate quantum chemistry calculations by up to a million times, fundamentally transforming chemical and materials sc... -
Physics-Informed Foundation Model “CLOUD,” Pre-trained on Over 6 Million Crystals, Revolutionizes Materials Property Prediction
springermedizin.de Germany Overview The "CLOUD" model, a scalable, physics-informed, Transformer-based foundation model for crystal representation learning, has been introduced. Pre-trained on over 6 million crystals, CLOUD encodes cryst...
