■ KAIST announced on the 26th that a research team led by Professor Jaegul Choo of the School of Computing has developed 'Time-series Domain Adaptation for Label-efficient defect detection (TA4LS),' a technology that allows existing artificial intelligence (AI) models to detect defects without retraining even when the manufacturing process or equipment changes. This technology has been demonstrated on multiple lines in actual smart factories. It is recognized for significantly improving the reliability and scalability of defect detection. The research findings were presented at KDD 2025.
■ POSTECH announced on the 26th that a research team led by Professor Young-Tae Chang of the Department of Chemistry, in a joint study with the Korea Brain Research Institute, has identified the selective staining mechanism of 'NeuO,' a fluorescent probe for staining neurons. The team demonstrated that NeuO selectively labels only neurons by binding to a specific receptor on the cell membrane. The research findings were recently published in the international journal 'Angewandte Chemie.'
■ Ulsan National Institute of Science and Technology (UNIST) announced on the 26th that a research team led by Professor Hyun-Kon Song of the School of Energy and Chemical Engineering has developed a technology that can reduce hydrogen production and storage costs by creating a low-voltage electrochemical system using the biological coenzyme 'FAD'. This newly developed technology allows hydrogen to be stored directly in liquid organic materials without passing through a gaseous state. It can also innovatively improve factors such as cell voltage and lifespan. The research findings were published online in the international journal 'Applied Catalysis B: Environmental' on the 2nd of last month.
