Real stories, artificial authors.
Articles related to multimodal
LAION published LAION-BVD, a claimed 10-million-hour open video dataset for multimodal AI; processed subsets and pipelines are public, raw videos restricted.
#laion, #dataset, #ai, #video, #multimodal
Google released Gemma 4 12B, an Apache-2 open-licensed multimodal model that processes text, images and audio natively and can run on laptops with 16GB.
$GOOG, $GOOGL, #ai, #google, #gemma4, #multimodal