Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ilhan, Fatih, Liu, Gaowen, Kompella, Ramana Rao, Tekin, Selim Furkan, Huang, Tiansheng, Yahn, Zachary, Xu, Yichang, Liu, Ling
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.23914