Crystal– tag –
-
arXiv Releases High-Information Dataset ‘MAD-1.6’ for Universal Atomistic Machine Learning, Boosting Predictive Accuracy
arXiv USA Overview The high-quality, high-information dataset 'MAD-1.6' has been released on arXiv to accelerate universal atomistic machine learning. Comprising 362,646 atomic structures across 102 chemical elements, it covers diverse m... -
Georgia Tech Researchers Awarded NSF CAREER Grants to Advance AI-Driven Design of Ferroelectric Semiconductors and Composites
Georgia Tech College of Engineering USA Overview Professor Laura G. Garten at Georgia Tech has received an NSF CAREER Award to advance AI-driven research systematically tuning the crystal structure, electric field response, and light abs... -
AI Materials Discovery Faces New Bottleneck in ‘Verification’: Only 0.2% of DeepMind GNoME Predictions Experimentally Validated
AI Invasion USA Overview While AI has effectively solved the 'generation problem' in protein structure prediction (AlphaFold) and material candidate discovery (GNoME), 'verification' has emerged as the new bottleneck. Only approximately ... -
Google DeepMind’s GNoME AI Discovers 2.2 Million New Crystal Structures, Equaling 800 Years of Experimental Data
Alcimed France Overview Google DeepMind's GNoME AI model has identified 2.2 million novel crystal structures, predicting 380,000 of them to be stable, an achievement comparable to 800 years of traditional experimental discovery. This bre... -
AI-Proposed Superconductor Generation Is Not Discovery: Physics Judge Highlights GNoME and MatterGen Limitations
arXiv USA Overview This paper introduces a 'physics judge' to assess whether AI-proposed superconductors possess necessary physical properties beyond mere thermodynamic stability. It critically evaluates generative models like GNoME and ... -
Physics-Aware AI Indispensable for Materials Research: Performance Gaps Highlighted in Thermal Conductivity Prediction
Columbia Engineering USA Overview Columbia Engineering emphasizes the critical need for physics-aware AI in materials science, particularly for machine learning interatomic potentials (MLPs) that predict macroscopic properties from quant... -
National University of Singapore Builds ‘AI Foundry’ to Transform Materials Discovery via Continuous Prediction, Experimentation, and Learning Cycle
EurekAlert! Singapore Overview Professor Ong is leading the Materialyze.AI Lab at NUS to establish an 'AI Foundry' for transforming materials discovery, aiming to connect various AI capabilities to create a continuous cycle of prediction... -
Google DeepMind GNoME and Microsoft MatterGen Accelerate Materials Discovery, Predicting Millions of Novel Stable Structures
Facebook (MIT DMSE) USA Overview Generative AI models, including Google DeepMind's GNoME and Microsoft's MatterGen, are significantly accelerating materials discovery by proposing novel material combinations and predicting their stabilit... -
Google DeepMind and MOFGen Synthesize Hundreds of Thousands of AI-Designed MOFs in Landmark Breakthrough
Springer Nature Community UK Overview A collaboration between Google DeepMind and MOFGen has led to the successful synthesis of the largest set of AI-designed materials to date. The MOFGen AI agent system autonomously proposes new Metal-... -
Closing the Loop in AI-Driven Biomedical Discovery: LLM Agents Generate Scientific Reasoning and Interpret Experimental Results
Preprints.org Switzerland Overview This article explores how to close the 'loop' from hypothesis to experiment and revised hypothesis in AI-driven scientific discovery. Large Language Model (LLM) agents are highlighted for their role in ...
