Mix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bohne, Jason, Polak, Pawel, Rosenberg, David, Bloniarz, Brian, Kazantsev, Gary
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!