VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models

Open Webpage

Ce Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu, Hongming Zhang, Zhisong Zhang, Haitao Mi, Dong Yu

Published: 2026, Last Modified: 11 Feb 2026Trans. Mach. Learn. Res. 2026EveryoneRevisionsBibTeXCC BY-SA 4.0