AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yonghui, Zhou, Wengang, Feng, Hao, Li, Houqiang
Format:	Preprint
Published:	2024
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/2408.16986