研究人员开发了一种优化生成模型离散化方法，旨在用有限的计算资源提高样本质量。这种方法被称为条件边际熵率目标，将概率路径的几何形状与边际分布的演变分离开来。将其应用于流匹配和薛定谔桥模型，在样本质量指标（如MMD和FID）方面显示出显著的改进，尤其是在低样本量情况下，并有望应用于蛋白质生成等领域。 AI
影响 以更少的计算步骤提高生成模型的样本质量，可能加速研究和应用开发。
排序理由 该集群包含两篇详细介绍生成模型和信息论新研究的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few function evaluations. Flow matching and Schrödinger bridges define probability paths, yet their inference grids are usually heuristic or …
arXiv:2605.16229v1 Announce Type: cross Abstract: Dependence among marginally constrained observations can break a finite-sample barrier. To formalize this phenomenon, we introduce the \emph{minimum list entropy coupling} $H(P\|Q_1,\dots,Q_m)$, the minimum conditional entropy $H(…
Dependence among marginally constrained observations can break a finite-sample barrier. To formalize this phenomenon, we introduce the \emph{minimum list entropy coupling} $H(P\|Q_1,\dots,Q_m)$, the minimum conditional entropy $H(X|Y_1,\dots,Y_m)$ over all joint distributions wit…