Google Trains User Interface and Infographics Understanding AI Model ScreenAI

Google Research recently developed ScreenAI, a multimodal AI model for understanding infographics and user interfaces. ScreenAI is based on the PaLI architecture and achieves state-of-the-art performance on several tasks.

ai ai model anthony architecture art computer vision deep learning google google research infographics interfaces ml & data engineering multimodal multimodal ai neural networks performance research state tasks trains understanding