QMoP: Query Guided Mixture-of-Projector for Efficient Visual Token Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zhongyang, Li, Yaqian, Fang, Faming, Takezoe, Rinyoichi, Bo, Zi-Hao, Qian, Cheng, Guang, Mo, Zhang, Guixu, Long, Kaiwen
Format:	Preprint
Published:	2026
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/2603.21232