通过聚类优化生成路径，让扩散模型跑得更快更准
COT-FM: Cluster-wise Optimal Transport Flow Matching
- 将目标样本聚类后，为每类配专属源分布，实现局部精准传输
- 生成轨迹更直，采样速度提升且图像质量显著改善
- 无需改动模型结构，适配各类生成任务的即插即用方案
我们提出COT-FM，一种重塑流匹配（FM）中概率路径的通用框架，以实现更快、更可靠的生成。传统FM模型常因随机或批次耦合产生弯曲轨迹，增加离散化误差并降低样本质量。COT-FM通过聚类目标样本，为每个簇分配由预训练FM模型反向得到的专用源分布，采用分而治之策略，实现更精确的局部传输，显著提升向量场的直线性，且不改变模型架构。作为即插即用方法，COT-FM在二维数据集、图像生成基准和机器人操控任务中均持续加速采样并提升生成质量。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。