notesum.ai

Published at December 5

VisionZip: Longer is Better but Not Necessary in Vision Language Models

cs.CV
cs.AI
cs.CL
cs.LG

Released Date: December 5, 2024

Authors: Senqiao Yang1, Yukang Chen1, Zhuotao Tian2, Chengyao Wang1, Jingyao Li1, Bei Yu1, Jiaya Jia3

Aff.: 1CUHK; 2HITSZ; 3HKUST

Arxiv: http://arxiv.org/pdf/2412.04467v1