Better Supervised Fine-tuning for VQA: Integer-Only Loss

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qian, Baihong, Fan, Haotian, Liao, Wenjie, Wang, Yunqiu, Li, Tao, Cui, Junhui
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.11170