Science

A new approach combines physics-based modeling with deep learning to rapidly assess frequency response and prevent widespread blackouts.

A new framework leverages graph neural networks to adaptively identify malicious activity within cloud-based Identity and Access Management systems.

A new framework combines advanced machine learning with economic indicators to deliver more accurate predictions for volatile construction material prices.

A new deep learning framework elegantly combines operator theory with neural networks to dramatically improve the accuracy of fluid dynamics predictions.

A new approach combines the power of large language models and attention mechanisms to achieve more accurate and robust text categorization.

New research leverages machine learning to accurately forecast how long it will take to contain wildfires in California, offering crucial insights for resource allocation and response strategies.

A new benchmark assesses language models’ ability to handle complex financial instructions, revealing surprising strengths in open-weight systems.

Researchers have developed a deep learning system that accurately predicts heatwave-related mortality by focusing on overall population health, rather than just heat-related deaths.

A new framework offers a lifecycle-based approach to managing AI risks and ensuring alignment with evolving global regulations.

Researchers have unveiled a comprehensive evaluation framework designed to rigorously assess the safety and compliance of large language models when applied to complex financial tasks.