100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chung, Yeounoh, Desai, Rushabh, He, Jian, Xiao, Yu, Hottelier, Thibaud, Samo, Yves-Laurent Kom, Khadilkar, Pushkar, Chen, Xianshun, Idicula, Sam, Özcan, Fatma, Halevy, Alon, Papakonstantinou, Yannis
Format:	Preprint
Published:	2026
Subjects:	Databases Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.15970