From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Suo, Yucheng, Ma, Fan, Zhu, Linchao, Wang, Tianyi, Rao, Fengyun, Yang, Yi
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/2503.20472