Science

A new approach combines graph neural networks with large language models to forecast congestion in major ports and provide clear, understandable explanations for potential disruptions.

As artificial intelligence systems become increasingly integrated into critical infrastructure, traditional cybersecurity approaches are proving inadequate, demanding a fundamental shift in how we detect and respond to emerging threats.

A new deep learning model leverages weather and traffic data to dramatically improve the accuracy of predicting where and when weather-related crashes will occur.

A guided approach using large language models promises to streamline risk assessment, but human oversight remains crucial for reliable results.

Researchers are leveraging deep neural networks to anticipate critical transitions in complex systems, offering a powerful new method for identifying points of instability.

A new deep learning model accurately predicts the evolution of supernova light curves, offering a crucial tool for real-time analysis of upcoming large-scale astronomical surveys.

A new reinforcement learning agent anticipates episodes of freezing of gait, offering a path towards more effective therapeutic interventions.

A new multi-agent system aims to improve clinical decision-making in fast-paced emergency departments by interpreting complex patient vital signs.

A new framework empowers artificial intelligence to actively select the most informative measurements from continuously changing physical environments, dramatically boosting predictive performance.

This research details a new system that automatically translates cyber threat intelligence into actionable firewall rules using the power of large language models and semantic reasoning.