Researchers in China have developed a self-supervised graph neural network that classifies the urgency of urban patrol cases without any...

A new benchmark study shows that data augmentation lifts pre-trained deep learning models to up to 98.06% accuracy in classifying...

Researchers have combined conditional diffusion models with graph neural networks to generate coordinated energy schedules for building clusters, achieving a...

Researchers at Ningxia University have developed SPMTNet, a structural-prior-guided multi-task AI framework that recognizes Tangut characters by learning their internal...

A new Predictive Uncertainty Curve framework turns how AI models wobble under perturbations into a powerful, shadow-model-free membership inference attack...

Virginia Tech will lead a $9.26 million NIH-funded, multi-institutional project using mathematical modeling, machine learning, and uncertainty quantification to predict...

A new study combining CMIP6 rainfall projections with deep learning shows that high landslide susceptibility zones in China's Qinling Mountains...

Researchers have developed MMA-HNS, a framework that keeps multimodal knowledge graph completion accurate even when the textual descriptions of entities...

Researchers in Turkey have built a multimodal Vision Transformer framework that converts Android app features into grayscale and QR code...

A new encoder–decoder transformer with waveform-level data augmentation achieves 100 percent accuracy on German emotional speech and 94 percent on...