SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yin, Yuanyang, Zhao, Yaqi, Zhang, Yajie, Zhang, Yuanxing, Lin, Ke, Wang, Jiahao, Tao, Xin, Wan, Pengfei, Zhang, Wentao, Zhao, Feng
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/2408.11813