Shulou(Shulou.com)11/24 Report--

CTOnews.com March 4 news, ChatGPT-based Bing chat has made many users feel the power of AI, and Microsoft recently launched a more powerful all-round AI-Kosmos-1. ChatGPT is a plain text LLM, whereas it is a more powerful Multi-Pattern Large Language Model (MLLM).

Kosmos-1 can analyze the content of images, solve visual puzzles, perform visual text recognition, pass visual IQ tests, understand natural language instructions, and more.

CTOnews.com learned from the report that Kosmos-1 can process content such as text, audio, images and video, building a versatile artificial intelligence that can process tasks like human minds.

"Multimodal perception, as a fundamental component of intelligence, is a necessary condition for achieving artificial intelligence," the researchers wrote in their academic paper. Visual examples in the Kosmos-1 paper show models analyzing images and answering questions about them, reading text from images, writing titles for images, and performing visual IQ tests with an accuracy of 22- 26 percent.

Microsoft says it plans to make Kosmos-1 available to developers, although the GitHub page referenced in the paper had no apparent Kosmos specific code at the time of publication.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.