Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Ruina, Wang, Chen, Wei, Lai, Bai, Jionghao, Yu, Bin, Huang, Weiran, Wang, Kai, Wang, Yue
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.30912