研究人员开发了一种名为时间重参数化累积强度外插（TR-CIE）采样器的新型采样方法，用于离散流匹配（DFM）。该方法旨在提高生成模型在离散状态空间上的采样质量，尤其是在函数评估次数有限的情况下。TR-CIE结合了基于调度的重参数化和累积强度外插规则，共同提高了累积强度的近似精度并减少了近似误差。该采样器每步需要一次函数评估，并在文本生成和文本到图像任务等各种基准测试中展示了改进的采样质量。 AI
影响 这种新型采样器可以提高生成模型的效率和质量，尤其是在计算资源有限的任务中。
排序理由 该集群包含一篇详细介绍用于离散流匹配的新型采样器的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.24140v1 Announce Type: new Abstract: Discrete flow matching (DFM) provides a principled framework for generative modeling on discrete state spaces via continuous-time Markov chain dynamics. In practice, sampling for DFM commonly employs discretizations such as $\tau$-l…
Discrete flow matching (DFM) provides a principled framework for generative modeling on discrete state spaces via continuous-time Markov chain dynamics. In practice, sampling for DFM commonly employs discretizations such as $τ$-leaping, yet efficient sampling methods under a limi…
Discrete flow matching (DFM) provides a principled framework for generative modeling on discrete state spaces via continuous-time Markov chain dynamics. In practice, sampling for DFM commonly employs discretizations such as $τ$-leaping, yet efficient sampling methods under a limi…