arXiv 2609.33803 · cs.LG · 2026-09-27
Diffusion Reward Models
Xiangyang Wang, Bingxiang He, Zeyuan Liu, Jiaze Wang, Ziqing Qiao, Yuxin Zuo, Huan-ang Gao, Cheng Qian and 8 more
Tsinghua NLP Group
In latest · #256 Added on 2026-10-21
One-line takeaway
Tsinghua's Diffusion Reward Model recasts reward modelling as conditional density estimation to capture multimodal human preferences.
清华 DRM 把奖励建模改成条件密度估计，用扩散模型刻画人类偏好的多峰分布。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Alignment
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.