LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
BibTex
Copy
@misc{zhuSun Oct 12 2025 15:42:47 GMT+0000 (Coordinated Universal Time)llada15variancereduced,
title={LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models},
author={Fengqi Zhu and Rongzhen Wang and Shen Nie and Xiaolu Zhang and Chunwei Wu and Jun Hu and Jun Zhou and Jianfei Chen and Yankai Lin and Ji-Rong Wen and Chongxuan Li},
year={Sun Oct 12 2025 15:42:47 GMT+0000 (Coordinated Universal Time)},
eprint={2505.19223},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2505.19223},
}