August 2026– date –
-
Physics-Informed Pairwise Charge Transfer GGNN Framework Achieves Fast, Universal Prediction of Dynamic Properties Under Electric Fields
ACS Publications USA Overview An ACS Publications paper reports a novel framework combining physics-informed Pairwise Charge Transfer (PQT) theory with a Generalized Global Neural Network (GGNN) for rapid and accurate prediction of dynam... -
Universal MLIPs Face Generalization Challenges, ACS Study Highlights Need for Iterative Fine-Tuning of Material-Specific Models
ACS Publications USA Overview An ACS Publications paper highlights that while Universal Machine Learning Interatomic Potentials (MLIPs) are rapidly becoming general tools for atomic simulations, their role in quantitative material modeli... -
Fine-Tuned MACE Foundation Model Develops Transferable MLP Predicting Water Adsorption in 420 Al-MOFs with DFT Accuracy
ACS Publications USA Overview This paper successfully developed a transferable machine learning potential (MLP) by fine-tuning a MACE foundation model to accurately predict water adsorption behavior in Metal-Organic Frameworks (MOFs). Tr... -
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... -
Machine Learning Interatomic Potentials (MLIPs) Accelerate Catalyst Discovery, Achieving DFT-Level Accuracy at Low Cost
nano-matter.com International Overview As of August 2026, Machine Learning Interatomic Potentials (MLIPs) have become a mainstream technology in computational catalyst research, enabling rapid screening of catalyst candidates, efficient ... -
Review Paper on AI-Driven Inverse Design of Functional Materials Forecasts Broad Applications from Energy Catalysis to Structural Materials
Scientific Research Publishing (SCIRP) International Overview A Scientific Research Publishing (SCIRP) paper provides a systematic review of progress and challenges in 'AI-enabled reverse design' of functional materials. The study analyz... -
Mitsubishi Chemical Integrates Generative AI, Quantum Computing, GPU Acceleration for EUV Photoresist Design
SEMICON Taiwan / Mitsubishi Chemical Japan Overview Mitsubishi Chemical is strategically integrating generative AI, quantum computing, and GPU-accelerated computing for next-generation material design, notably for EUV photoresist materia... -
MIT’s CrysVCD Framework Achieves 70% Stability in AI Crystal Material Design at Generation Stage, Significantly Boosting Efficiency
Superpower Daily USA Overview MIT researchers have developed the CrysVCD framework, combining language and diffusion models to dramatically improve the chemical stability of AI-designed crystalline materials at the generation stage, sign... -
AI Material Discovery Outpaces Experimental Validation: Calls for Standardized ‘AI Evidence Passport’ Infrastructure
Eurasia Review USA Overview While generative AI significantly boosts the discovery of novel material candidates, the pace of experimental synthesis, characterization, and manufacturing validation lags behind AI's generative speed, creati... -
NUS Launches ‘AI Foundry’ to Accelerate New Material Discovery from Months to Weeks
NUS News Singapore Overview The National University of Singapore (NUS), led by Professor Shyue Ping Ong, has established an 'AI Foundry' integrating AI, scientific data, and automated experimentation to dramatically shorten the new mater...
