Energy-Based Diffusion Language Models for Text Generation

方法与贡献

在每一步扩散去噪分布中加入完整序列的残差能量，采用自回归模型或 NCE 参数化，并通过并行重要性采样生成文本。

直接引用 Deng 等人（2020），将残差修正与配分函数估计用于扩散语言建模。

结合主题阅读

基于能量的文本生成：残差模型、重采样与扩散 →

引用

Minkai Xu, Tomas Geffner, Karsten Kreis, Weili Nie, Yilun Xu, Jure Leskovec, Stefano Ermon, Arash Vahdat. Energy-Based Diffusion Language Models for Text Generation. ICLR 2025.

@inproceedings{edlm,
  title = {{Energy-Based Diffusion Language Models for Text Generation}},
  author = {Xu, Minkai and Geffner, Tomas and Kreis, Karsten and Nie, Weili and Xu, Yilun and Leskovec, Jure and Ermon, Stefano and Vahdat, Arash},
  year = {2025},
  booktitle = {ICLR 2025},
  url = {https://arxiv.org/html/2410.21357v4},
  eprint = {2410.21357},
  archivePrefix = {arXiv}
}