COT-FM: Cluster-wise Optimal Transport Flow Matching
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915861457010688 |
|---|---|
| author | Chiang, Chiensheng Tu, Kuan-Hsun Liao, Jia-Wei Chou, Cheng-Fu Ke, Tsung-Wei |
| author_facet | Chiang, Chiensheng Tu, Kuan-Hsun Liao, Jia-Wei Chou, Cheng-Fu Ke, Tsung-Wei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13395 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | COT-FM: Cluster-wise Optimal Transport Flow Matching Chiang, Chiensheng Tu, Kuan-Hsun Liao, Jia-Wei Chou, Cheng-Fu Ke, Tsung-Wei Computer Vision and Pattern Recognition Machine Learning Robotics 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. |
| title | COT-FM: Cluster-wise Optimal Transport Flow Matching |
| topic | Computer Vision and Pattern Recognition Machine Learning Robotics |
| url | https://arxiv.org/abs/2603.13395 |