A research team has developed a new hybrid artificial intelligence framework that can accurately estimate leaf nitrogen content without relying on labor-intensive field measurements.

A research team has developed a new model, PlantIF, that addresses one of the most pressing challenges in agriculture: the accurate and timely diagnosis of plant diseases.

A research team has developed CornPheno, a smartphone-based tool designed to revolutionize corn phenotyping.

A research team has developed a method for improving crop growth monitoring by accurately estimating the fraction of absorbed photosynthetically active radiation (fAPAR) throughout the entire rice growth cycle.

Humans possess a remarkable balance between stability and flexibility, enabling them to quickly establish new plans and adjust goals even in the face of sudden changes. However, "Model-Free reinforcement learning," which is widely used in robotics and exemplified by AlphaGo’s famous match against Lee Sedol, struggle to achieve these two capabilities simultaneously. KAIST's research team has discovered that the secret lies in the unique information processing method within the prefrontal cortex, a principle that could serve as the foundation for developing "Brain-like AI” that is both flexible and stable.

Layered double hydroxides (LDHs) are emerging as promising electrocatalysts for the oxygen evolution reaction (OER), a key barrier in clean hydrogen production. However, their catalytic performance has long been restricted by limited active sites, sluggish electron transfer, and structural instability under operational conditions. A new review summarizes how electronic defect engineering, including vacancy creation, heteroatom doping, single-atom incorporation and lattice modulation, which reconfigures electron distribution, enhances active site exposure, accelerates reaction kinetics, and strengthens catalytic durability. The work highlights strategies that effectively lower OER overpotential and improve stability by tuning LDH atomic coordination environments, providing a unified framework for the design of next-generation high-performance water-splitting catalysts.

Medical image segmentation is a fundamental component of many clinical applications such as computer-aided diagnosis, radiotherapy planning, and preoperative planning. Its accuracy and stability directly affect subsequent quantitative analysis and clinical decision-making. Based on a systematic analysis of feature utilization in U-shaped architectures, Prof. Zhao Qi’s team at Liaoning University of Science and Technology and Prof. Shuai Jianwei’s team at the Wenzhou Institute of the University of Chinese Academy of Sciences have developed an E-shaped medical image segmentation framework that differs from conventional symmetric decoders.