GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO

10 June 2025

ArXiv (abs)PDF HTML

Papers citing "GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO"

Title
No papers