AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Qi, Ruan, Jingqing, Li, Hao, Zhao, Haodong, Wang, Desheng, Chen, Jiansong, Guanglu, Wan, Cai, Xunliang, Zheng, Zhi, Xu, Tong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.07165