# Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference

> Research article (Proceedings of the AAAI Conference on Artificial Intelligence, 2025) · cited 15× · AI/ML

**Wikidata**: [openalex:W4409367031](https://www.wikidata.org/wiki/openalex:W4409367031)  
**Source**: https://4ort.xyz/entity/boosting-multimodal-large-language-models-with-visual-tokens-withdrawal-for-rapid-inference
