# Align before Fuse: Vision and Language Representation Learning with Momentum Distillation

> Research article (Neural Information Processing Systems, 2021) · cited 17× · AI/ML

**Wikidata**: [openalex:W3211483028](https://www.wikidata.org/wiki/openalex:W3211483028)  
**Source**: https://4ort.xyz/entity/align-before-fuse-vision-and-language-representation-learning-with-momentum-distillation