conftrace_

reward difference prediction

2 papers

Explore in graph

Also known as

RDP

Co-occurring keywords · papers mentioning both

offline rlhf (1) reward fine-tuning (1) proximal update (1) sample reweighting (1) ranking loss (1) foundation model (1) diffusion model (1) language model alignment (1) preference learning (1) image generation (1)

Papers

PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models CVPR 2024 Reward Difference Optimization For Sample Reweighting In Offline RLHF EMNLP 2024