A new general-purpose model with unprecedented breadth, Unified-IO can handle a wide array of vision and language tasks. — A new model from AI2’s PRIOR team, Unified-IO is the first neural model to perform a large and diverse set of AI tasks spanning classical computer vision (including object detection, segmentation, and depth estimation), image synthesis (including image generation and image in-painting), vision-and-language (including visual question answering, image captioning and…