SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Haoyu, Huang, Jinfa, Wan, Zhongwei, Zheng, Xiawu, Ji, Rongrong, Luo, Jiebo
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/2603.23483