Cite
Notes
Only stored in your browser.
Attribution
DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models
arXiv 2025
from 1 papers
Joey Tianyi Zhou
Ruizhe Chen
Soujanya Poria
Wenhao Chai
Xiaotian Zhang
Zhifei Yang
Zuozhu Liu