VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qin, Guangshuo, Li, Zhiteng, Chen, Zheng, Zhang, Weihang, Kong, Linghe, Zhang, Yulun
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/2602.01037