GroupDPO: Memory efficient Group-wise Direct Preference Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leng, Jixuan, Si, Si, Yu, Hsiang-Fu, Raman, Vinod, Dhillon, Inderjit S.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!