Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Open Webpage

Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Shaohui Lin

Published: 01 Jan 2025, Last Modified: 04 Jun 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0