Category

Vision & multimodal

AI that reads images, video, audio and documents: new multimodal research on vision-language models and document AI, rated for real-world readiness.

Follow Vision & multimodal
IIIOpen sourcePreprint

Google's PARDIG maps global rainfall, trained only on satellite radar

A Google DeepMind and Google Research model turns weather data and satellite images into rain maps every 15 minutes. In the authors' tests it beats the main existing products, most clearly in heavy rain. The paper is a preprint and has not been peer reviewed.