Breaking the Factorization Barrier in Diffusion Language Models

方法与贡献

CoDD 将因子化扩散预测与可进行高效推断的概率电路先验组合，建模 token 之间的联合依赖。

与结构化生成一样，将并行神经网络打分和联合概率推断分开处理。

结合主题阅读

结构化解码：高阶 CRF、扩散语言模型与候选格 →

引用

Ian Li, Zilei Shao, Benjie Wang, Rose Yu, Guy Van den Broeck, Anji Liu. Breaking the Factorization Barrier in Diffusion Language Models. ICML 2026.

@inproceedings{li2026factorization,
  title = {{Breaking the Factorization Barrier in Diffusion Language Models}},
  author = {Li, Ian and Shao, Zilei and Wang, Benjie and Yu, Rose and Van den Broeck, Guy and Liu, Anji},
  year = {2026},
  booktitle = {ICML 2026},
  url = {https://proceedings.mlr.press/v306/li26fd.html},
  eprint = {2603.00045},
  archivePrefix = {arXiv}
}