Researchers have unveiled a Trustworthy AI pipeline that embeds privacy, fairness, security, robustness, safety, and explainability across the entire development...

A systematic benchmark of classical, transformer-based and foundation AI models finds that a hybrid CNN-foundation-transformer architecture more than doubles the...

Researchers at Hefei University have developed AMCF, a multimodal AI model that combines bidirectional text-image attention with dual-branch gated fusion...

A new framework called LACE uses large language models and complementary evolution to automatically design teams of specialist heuristics that...

A systematic review of 257 studies maps three decades of research on artificial intelligence in public policy, identifying six themes...

Researchers have introduced a Riemannian manifold-based loss function that pushes multimodal Transformer models to state-of-the-art accuracy in human activity recognition...

Researchers have combined lattice light sheet microscopy, structured illumination and a transformer-based AI model to achieve twofold-beyond-diffraction 3D super-resolution imaging...

Researchers have built a phishing detection framework that pairs a lightweight hybrid deep learning model with LIME and SHAP explanations...

Researchers have developed a personalized N-of-1 transformer framework that learns an individual's daily behavior patterns from smart home activity logs...

Researchers at Bahir Dar University have built an ensemble lip-reading model for Amharic that combines Gabor filters, Capsule Networks, and...