# MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

> Research article (2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025) · cited 13× · AI/ML

**Wikidata**: [openalex:W4413145987](https://www.wikidata.org/wiki/openalex:W4413145987)  
**Source**: https://4ort.xyz/entity/mmaudio-taming-multimodal-joint-training-for-high-quality-video-to-audio-synthesis