HSD: Training-Free Acceleration for Document Parsing Vision-Language Model with Hierarchical Speculative Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liao, Wenhui, Li, Hongliang, Xie, Pengyu, Cai, Xinyu, Shen, Yufan, Xin, Yi, Qin, Qi, Ye, Shenglong, Li, Tianbin, Hu, Ming, He, Junjun, Liu, Yihao, Wang, Wenhai, Dou, Min, Fu, Bin, Shi, Botian, Qiao, Yu, Jin, Lianwen
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.12957