Multimodal Large Language Model RSS

GPT-4 is coming next week – and it will be multimodal, says Microsoft Germany The release of GPT-4 is imminent, as Microsoft Germany CTO Andreas Braun mentioned at an AI kickoff event on March 9, 2023. GPT-4 is coming next week: at an approximately one-hour hybrid information event entitled " AI in Focus - Digital Kickoff " on 9 March 2023, four Microsoft Germany employees presented Large Language Models (LLM) like GPT series as a disruptive force for companies and their Azure-OpenAI offering in detail. The kickoff event took place in the German language, news outlet Heise was present. Rather casually, Andreas Braun, CTO...

A big convergence of language, multimodal perception, action, and world modeling is a key step toward general artificial cognition.   In this work, we introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i.e., few-shot), and follow instructions (i.e., zero-shot). We train Kosmos-1 from scratch on web-scale multimodal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. We evaluate various settings, including zero-shot, few-shot, and multimodal chain-of-thought prompting, on a wide range of tasks without any gradient updates or finetuning. Experimental results show that Kosmos-1 achieves impressive performance on (i)...