Mitigating Hallucinations in Video Large Language Models via Spatiotemporal-Semantic Contrastive Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Yuansheng, Zhao, Jinman, Zhang, Tong, Xu, Xingguo, Bao, Han, Wang, Zonghui, Chen, Wenzhi
Format:	Preprint
Published:	2026
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/2601.22574