A new contrastive-learning framework enables hyperspectral classification with few labels. It masks redundant spatial and spectral information, mixes samples into positive pairs, and separates spatial and spectral features.

Researchers investigated how quantum computing could improve machine learning when healthcare data are limited. Testing five computing frameworks, the team found that a quantum support vector machine using D-Wave Quantum Inc. technology achieved up to 94.31% accuracy in predicting lung cancer from symptoms and risk factors. The findings demonstrate the potential of quantum machine learning for healthcare applications, while representing preliminary results that require further validation before clinical use.

A robotics competition-based education program at Okayama University of Science in Japan has received a 2024 Engineering Education Award from the Japanese Society for Engineering Education. Developed over more than 15 years, the program uses hands-on engineering challenges and project-based learning to help students develop essential professional skills, including teamwork, problem-solving, and the ability to learn from setbacks.

A new study from Nanjing University reveals that many AI models used for software development may be built on shaky ground—low-quality training data. Published on 15 September 2026, in Frontiers of Computer Science, this systematic literature review is the first to focus on data preparation and quality issues in code-centric generative software engineering tasks (GSETs), such as code summarization, generation, repair, and translation.