Multimodal artificial intelligence (MLLM) could be the key to the development of artificial general intelligence, a technology that could in the future replace humans in any intellectual task or work.
Kosmos-1 is a multimodal model developed by Microsoft researchers. Last Monday, it was unveiled as a model capable of:
The development of theArtificial intelligence multimodal is seen as a crucial step towards creating an artificial general intelligence (AGI) capable of performing general human-level tasks.
“Being a fundamental part of intelligence, multimodal perception is a necessity to achieve artificial general intelligence, in terms of knowledge acquisition and real-world embedment,” the researchers write in their academic paper, Language Is Not All You Need: Aligning Perception with Language Model.
The Kosmos-1 model can analyze images and answer questions about them, read text from an image, write captions for images, and score between 22 and 26 percent on a visual IQ test, such as demonstrated in the visual examples in the Kosmos-1 study.
OpenAI, Microsoft's key business partner in artificial intelligence, has set AGI as its primary focus. Kosmos-1 appears to be an exclusive initiative of Microsoft, without the assistance of OpenAI.
BlogInnovazione.it
Developing fine motor skills through coloring prepares children for more complex skills like writing. To color…
The naval sector is a true global economic power, which has navigated towards a 150 billion market...
Last Monday, the Financial Times announced a deal with OpenAI. FT licenses its world-class journalism…
Millions of people pay for streaming services, paying monthly subscription fees. It is common opinion that you…