# MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

> Research article (2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024) · cited 15× · AI/ML

**Wikidata**: [openalex:W4402754149](https://www.wikidata.org/wiki/openalex:W4402754149)  
**Source**: https://4ort.xyz/entity/madtp-multimodal-alignment-guided-dynamic-token-pruning-for-accelerating-vision-language-transformer