Apple reveals AI model that can interpret photos and count objects [TechSpot]
View Article on TechSpot
Apple researchers have developed MM1, a new approach for training large language models (LLMs) that incorporate both textual and visual information. MM1 is part of a family of multimodal models that includes up to 30 billion parameters, utilizing a dataset comprising image-caption pairs, interleaved image-text documents, and text-only data, according…