Materials Informatics– category –
-
AI-Driven Precision: LSBoost Ensemble ML Revolutionizes Defect Management in Additive Manufacturing
MDPI Switzerland Overview This research introduces a novel machine learning approach utilizing decision tree LSBoost ensembles to significantly enhance quality control and reproducibility in additively manufactured parts, particularly th... -
Active Learning for MACE-MP-0 Foundation MLFFs Achieves Full Data Accuracy with Significantly Fewer Labeled Training Examples
arXiv International Overview This study demonstrates an innovative active learning strategy for fine-tuning machine-learning force fields (MLFFs), specifically focusing on foundation models like MACE-MP-0, to achieve full-data accuracy w... -
Functional Classification and XGBoost Integration with 10,000+ Semiconductor/Insulator Data Significantly Boosts Electronic Bandgap Prediction Accuracy
AIP Publishing USA Overview This research systematically investigates how functional classification of electronic bandgaps in over 10,000 semiconductors and insulators significantly improves machine learning model accuracy. Utilizing a P... -
Pauli Charges Dramatically Enhance Accuracy and High-Pressure, High-Temperature Stability of Machine-Learned Interatomic Potentials
ChemRxiv International Overview This research significantly improves machine-learned interatomic potentials (MLIPs) by integrating Pauli repulsion into a combination of machine-learned pair potentials and short-range atomic neural networ... -
Scalable Isotropic Message Passing ML Accelerates Electronic Structure and Atomistic Property Modeling by Efficiently Describing Non-Local Effects
The Journal of Chemical Physics | AIP Publishing USA Overview A new study demonstrates a scalable machine learning approach for isotropic message passing, leveraging continuous products of external potentials to model electronic structur... -
UniFFBench Reveals Critical Role of System-Specific Fine-Tuning for Universal ML Force Fields via Rigorous Experimental Benchmarking of 6 EGraFF Algorithms
ResearchGate International Overview The UniFFBench study rigorously evaluates universal machine learning interatomic potentials (uMLIPs) from six prominent EGraFF algorithms—NequIP, Allegro, BOTNet, MACE, Equiformer, and TorchMDNet—again... -
CuspAI Forges AI Materials Foundry: A Global Alliance with NVIDIA, Meta, and Samsung to Revolutionize Discovery
imec Belgium Overview CuspAI has launched the 'AI Materials Foundry,' a global network comprising over 30 founding members, including NVIDIA, Meta, Samsung, and Tokyo Electron, to significantly accelerate AI-powered materials discovery. ... -
MatterChat: Fusing Atomic Structures and Natural Language for Breakthroughs in Materials Science
OAE Publishing Inc. International Overview MatterChat, a pioneering multimodal large language model (LLM) for materials science, achieves a significant breakthrough by seamlessly integrating atomic structure encoding with natural languag... -
Generative AI System (GSDS) Accelerates De Novo Solvent Design for Alkali Metal Batteries
ACS Nano USA Overview A new Generative Solvent Design System (GSDS) has been introduced for de novo solvent design in rechargeable batteries, integrating a graph-based deep molecular generator with machine learning property predictors. T... -
Materials Informatics Weekly Report July 19, 2026
▼ ▼ ▼ If the infographic makes you want to read the full report, please click the download button below. ▼ ▼ ▼ 📄 Weekly Report July 19, 2026 (PDF) — Download Weekly Report July 19, 2026 (PDF) — DownloadDownload 🎙 Podcast July 19, 2026 (...
