COT-FM：簇级最优传输流匹配

摘要

我们提出COT-FM框架，该框架通过重构流匹配（FM）中的概率路径实现更快速、更稳定的生成。传统FM模型因随机或批量耦合常产生弯曲轨迹，导致离散化误差增大并降低生成质量。COT-FM通过聚类目标样本，并为每个聚类分配通过反向预训练FM模型获得的专用源分布，从而解决这一问题。这种分治策略在不改变模型架构的前提下，实现了更精确的局部传输和显著平直化的向量场。作为即插即用方案，COT-FM在二维数据集、图像生成基准测试及机器人操作任务中持续加速采样并提升生成质量。

English

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 batchwise 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 generation benchmarks, and robotic manipulation tasks.

COT-FM：簇级最优传输流匹配

COT-FM: Cluster-wise Optimal Transport Flow Matching

摘要

Support