EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tan, Zhiyu, Yang, Xiaomeng, Qin, Luozheng, Yang, Mengping, Zhang, Cheng, Li, Hao
Format:	Preprint
Published:	2024
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/2406.16562