# VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

> Research article (Advances in Neural Information Processing Systems 36, 2023) · cited 10× · AI/ML

**Wikidata**: [openalex:W7133188694](https://www.wikidata.org/wiki/openalex:W7133188694)  
**Source**: https://4ort.xyz/entity/vast-a-vision-audio-subtitle-text-omni-modality-foundation-model-and-dataset