Award-winning paper in ICML 2024 on “VideoPoet: A large language model for zero-shot video generation.”
Citation
VideoPoet: A large language model for zero-shot video generation Best Paper Proceedings Article
In: Proceedings of International Conference on Machine Learning (ICML), 2024.
Awarded the Best Paper Award by ICML 2024. More details at the Project Website.
Abstract
We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/
![](https://www.irfanessa.gatech.edu/wp-content/uploads/2024/07/videoframe_1026-1024x502.png)