Apple introduced Ferret-UI, a multimodal large language model, to enhance Siri's understanding of app layouts on iPhone displays.
Apple unveiled a new AI model, Ferret-UI, a multimodal large language model (MLLM) capable of understanding mobile user interface (UI) screens. Ferret-UI could improve Siri's understanding of app layouts on iPhone displays, potentially expanding its capabilities. The AI model, which recognizes app icons and small text, could also benefit visually impaired users and developers doing UI testing.
April 09, 2024
4 Articles