COT-FM：簇级最优传输流匹配
COT-FM: Cluster-wise Optimal Transport Flow Matching
把目标样本聚类并为每个簇反演一个专属源分布，从而拉直流匹配的向量场——这是一个与模型架构无关的即插即用模块，可直接套到已有的图像生成/编辑流匹配模型上以减少采样步数、提升样本质量。
原文依据 COT-FM fixes this by clustering target samples and assigning each cluster a dedicated source distribution obtained by reversing pretrained FM models.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 COT-FM，一个重塑流匹配（FM）概率路径以实现更快、更可靠生成的通用框架。由于随机耦合或批次耦合，FM 模型往往产生弯曲的轨迹，从而增大离散化误差并降低样本质量。COT-FM 通过聚类目标样本、并为每个簇分配一个由反转预训练 FM 模型得到的专属源分布来解决该问题。这种分而治之的策略带来更精确的局部传输和显著更直的向量场，且无需改变模型架构。作为一种即插即用的方法，COT-FM 在二维数据集、图像基准以及机器人操作任务上一致地加速采样并提升生成质量。
英文原文摘要 772 字符
We introduce COT-FM, a general framework that reshapes the probability path in Flow Matching (FM) to achieve faster and more reliable generation. FM models often produce curved trajectories due to random or batch-wise couplings, which increase discretization error and reduce sample quality. COT-FM fixes this by clustering target samples and assigning each cluster a dedicated source distribution obtained by reversing pretrained FM models. This divide-and-conquer strategy yields more accurate local transport and significantly straighter vector fields, all without changing the model architecture. As a plug-and-play approach, COT-FM consistently accelerates sampling and improves generation quality across 2D datasets, image benchmarks, and robotic manipulation tasks.