Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Kevin Y., Goyal, Sachin, Semedo, Joao D., Kolter, J. Zico
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2411.03312