On Monday, researchers from Microsoft introduced Kosmos-1, a multimodal model that can reportedly analyze images for content, solve visual puzzles, perform visual text recognition, pass visual IQ ...

Cohere's Command A Vision can read graphs and PDFs to make enterprise research richer and analyze the documents businesses actually rely on.

(RTTNews) - Chinese tech giant Alibaba Cloud on Wednesday unveiled its latest visual-language model, Qwen2.5-VL, which it claims to be a significant improvement from its predecessor, Qwen2-VL.

Microsoft could use these models to scrape and summarize information from Teams Meetings transcripts, and then add images generated from OpenAI’s Dall-E 2 image generation model to PowerPoint ...