Image Recognition
Microsoft has unveiled 'Kosmos-1', a multimodal large language model (MLLM) that can not only respond to language prompts but also visual cues. As per Microsoft, Kosmos-1 showed good results in image captioning, visual question answering and vision tasks, such as image recognition with descriptions. Kosmos-1 could pave the way for the next stage beyond ChatGPT's text prompts, reports said. Ananya Goyal / 04:31 pm on short byon