Active Learning– tag –
-
Preprints.org Publishes Review on High-Entropy Alloy Design: ML Addresses Combinatorial Explosion in Discovery
Preprints.org Unknown Overview A review paper published on Preprints.org explores the convergence of physical metallurgy and data-driven methods in high-entropy alloy (HEA) design. The paper details how AI and machine learning (ML) addre... -
Integrated Active Learning and Knowledge Distillation in MLMD Achieves 1/3 Data Efficiency with MACE Model, Outperforming DeePMD
ACS Publications USA Overview This study developed data-efficient and fast Machine Learning Molecular Dynamics (MLMD) interatomic potentials (MLIPs) by combining DeePMD and MACE models within an active learning and knowledge distillation... -
AI and Polymer Informatics Slash Material Development Time from Decades to Months
ChemCopilot USA Overview AI, machine learning, and polymer informatics frameworks are dramatically accelerating polymer R&D, potentially reducing the development cycle for novel commercial polymers from 10-15 years to mere months or ... -
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... -
University of Toronto’s AI Autonomous Lab Discovers Six New 3D-Printable Metal Alloys, Outperforming Inconel 625 in Weeks, for Aerospace and Advanced Manufacturing
Acceleration Consortium - University of Toronto / U of T Engineering News Canada Overview Researchers at the University of Toronto's Acceleration Consortium used an AI-driven autonomous lab to discover six new 3D-printable metal alloys t... -
arXiv Paper Demonstrates Full-Data Accuracy with Fewer Labels in ML Force Field Training Through Data Selection Strategy
arXiv International Overview This paper investigates the critical role of data selection in training and fine-tuning machine-learning force fields (MLFFs), demonstrating that active learning strategies like LLPR (Least-Likely to Predict ... -
Springer Nature Launches Call for Papers on ML Methods for Crystalline Defects, Emphasizing Integration with Atomic Simulations
Research Communities (Springer Nature) International Overview Research Communities by Springer Nature has initiated a call for papers focusing on machine learning (ML) methods for modeling and predicting crystalline defects. The call enc... -
AI to Accelerate Energy Materials Discovery: NUS Announces 2026 Workshop
National University of Singapore (NUS) Singapore Overview The National University of Singapore (NUS) will host an "AI for Energy Materials" workshop on July 10, 2026, co-located with the Solid State Ionics Conference 2026. Bringing toget... -
AI-Driven Design Transforms Metal-Organic Materials to Dynamic Networks, Powering Self-Driving Labs for Accelerated Discovery
MDPI International Overview This paper proposes extending AI-driven design of metal-organic materials (MOMs) beyond traditional crystalline MOFs to dynamic coordination networks, such as metal-polyphenol networks (MPNs). It integrates pr... -
arXiv Paper Presents ‘AutoPot’: Automated, Massively Parallel Workflow for Constructing Machine-Learning Potentials
arXiv USA Overview A new preprint on arXiv introduces 'AutoPot,' an automated and massively parallelized workflow for constructing Machine Learning Interatomic Potentials (MLIPs). MLIPs bring quantum accuracy to atomic modeling, enabling...
1