Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Guanyu, Wu, Qiucheng, Zhang, Yang, Wang, Zhaowen, Zhao, Handong, Chang, Shiyu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.22836