Learning Straight Flows: Variational Flow Matching for Efficient Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908669353918464 |
|---|---|
| author | Ma, Chenrui Xiao, Xi Wang, Tianyang Wang, Xiao Shen, Yanning |
| author_facet | Ma, Chenrui Xiao, Xi Wang, Tianyang Wang, Xiao Shen, Yanning |
| contents | Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent interpolant intersections or introducing consistency and mean-velocity modeling to promote straight trajectory learning. However, these approaches often suffer from discrete approximation errors, training instability, and convergence difficulties. To tackle these issues, in the present work, we propose \textbf{S}traight \textbf{V}ariational \textbf{F}low \textbf{M}atching (\textbf{S-VFM}), which integrates a variational latent code representing the ``generation overview'' into the Flow Matching framework. \textbf{S-VFM} explicitly enforces trajectory straightness, ideally producing linear generation paths. The proposed method achieves competitive performance across three challenge benchmarks and demonstrates advantages in both training and inference efficiency compared with existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17583 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Straight Flows: Variational Flow Matching for Efficient Generation Ma, Chenrui Xiao, Xi Wang, Tianyang Wang, Xiao Shen, Yanning Machine Learning Computer Vision and Pattern Recognition Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent interpolant intersections or introducing consistency and mean-velocity modeling to promote straight trajectory learning. However, these approaches often suffer from discrete approximation errors, training instability, and convergence difficulties. To tackle these issues, in the present work, we propose \textbf{S}traight \textbf{V}ariational \textbf{F}low \textbf{M}atching (\textbf{S-VFM}), which integrates a variational latent code representing the ``generation overview'' into the Flow Matching framework. \textbf{S-VFM} explicitly enforces trajectory straightness, ideally producing linear generation paths. The proposed method achieves competitive performance across three challenge benchmarks and demonstrates advantages in both training and inference efficiency compared with existing methods. |
| title | Learning Straight Flows: Variational Flow Matching for Efficient Generation |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.17583 |