TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Haokui, Ou, Congyang, Yan, Dawei, Wang, Peng, Yan, Qingsen, Zhang, Yu, Li, Ying, Xiao, Rong
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.04657