Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Qizhe, Cheng, Aosong, Lu, Ming, Zhang, Renrui, Zhuo, Zhiyong, Cao, Jiajun, Guo, Shaobo, She, Qi, Zhang, Shanghang
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.01818