# Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action

> Research article (2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024) · cited 53× · AI/ML

**Wikidata**: [openalex:W4402727574](https://www.wikidata.org/wiki/openalex:W4402727574)  
**Source**: https://4ort.xyz/entity/unified-io-2-scaling-autoregressive-multimodal-models-with-vision-language-audio-and-action