Microsoft has revealed Kosmos-1, a new AI model, as the battle over chatbots with artificial intelligence (AI) has intensified in recent months. In addition to text-based instructions or messages, the new model can also react to visual cues or visuals.
The user can benefit from a variety of new tasks, such as visual question answering and image captioning, with the multimodal large language model (MLLM). Beyond ChatGPT‘s text prompts, Kosmos-1 might pave the path for the subsequent step.
