A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911657560637440 |
|---|---|
| author | Ingebrand, Tyler Zhao, Ruihan Gupta, Kushagra Fridovich-Keil, David Chinchali, Sandeep P. Topcu, Ufuk |
| author_facet | Ingebrand, Tyler Zhao, Ruihan Gupta, Kushagra Fridovich-Keil, David Chinchali, Sandeep P. Topcu, Ufuk |
| contents | While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this end, we propose Function Projection for Flow Matching (FP-FM), an algorithm that directly conditions generation on samples from the target distribution. FP-FM learns basis functions to span the velocity fields corresponding to a set of training distributions, and adapts to new distributions by computing a simple least-squares projection onto this basis. This enables efficient generation of samples from diverse target distributions without additional training at inference time. We further introduce multiple variants of FP-FM that provide a trade-off in expressivity and compute by enriching the coefficient calculation, e.g., by making the coefficients dependent on time. FP-FM achieves greatly improved precision and recall relative to baselines across synthetic and image-based datasets, with especially strong gains on unseen distributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06272 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions Ingebrand, Tyler Zhao, Ruihan Gupta, Kushagra Fridovich-Keil, David Chinchali, Sandeep P. Topcu, Ufuk Machine Learning While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this end, we propose Function Projection for Flow Matching (FP-FM), an algorithm that directly conditions generation on samples from the target distribution. FP-FM learns basis functions to span the velocity fields corresponding to a set of training distributions, and adapts to new distributions by computing a simple least-squares projection onto this basis. This enables efficient generation of samples from diverse target distributions without additional training at inference time. We further introduce multiple variants of FP-FM that provide a trade-off in expressivity and compute by enriching the coefficient calculation, e.g., by making the coefficients dependent on time. FP-FM achieves greatly improved precision and recall relative to baselines across synthetic and image-based datasets, with especially strong gains on unseen distributions. |
| title | A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.06272 |