Google Announces Video Generation LLM VideoPoet

Google Research recently published their work on VideoPoet, a large language model (LLM) that can generate video. VideoPoet was trained on 2 trillion tokens of text, audio, image, and video data, and in evaluations by human judges its output was preferred over that of other models.

ai anthony audio data deep learning generate generative-ai google google research human image judges language language model large language large language model large language models llm ml & data engineering neural networks research text tokens video video data video generation videopoet work