Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.27147 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917513741205504 |
|---|---|
| author | Huang, Jerry Y. Lin, Justin Shah, Sheel Nair, Kartik Boffi, Nicholas M. |
| author_facet | Huang, Jerry Y. Lin, Justin Shah, Sheel Nair, Kartik Boffi, Nicholas M. |
| contents | In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing guidance methods either require expensive multi-particle, many-step schemes or rely on poorly understood approximations. We reformulate guidance as a \textit{deterministic optimal control problem}, yielding a hierarchy of algorithms that subsumes existing approaches at the coarsest level. We show that the \textit{flow map}, an object of significant recent interest for its role in fast inference, arises naturally in the optimal solution. Based on this observation, we propose \textbf{Flow Map Reward Guidance (FMRG)}: a training-free, \textit{single-trajectory} framework that uses the flow map to both integrate and guide the flow. At text-to-image scale, FMRG matches or surpasses baselines across inverse problems and reward-guided generation with \textbf{as few as 3 NFEs}, giving at least an order-of-magnitude speedup in comparison to prior state of the art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27147 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance Huang, Jerry Y. Lin, Justin Shah, Sheel Nair, Kartik Boffi, Nicholas M. Machine Learning Artificial Intelligence In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing guidance methods either require expensive multi-particle, many-step schemes or rely on poorly understood approximations. We reformulate guidance as a \textit{deterministic optimal control problem}, yielding a hierarchy of algorithms that subsumes existing approaches at the coarsest level. We show that the \textit{flow map}, an object of significant recent interest for its role in fast inference, arises naturally in the optimal solution. Based on this observation, we propose \textbf{Flow Map Reward Guidance (FMRG)}: a training-free, \textit{single-trajectory} framework that uses the flow map to both integrate and guide the flow. At text-to-image scale, FMRG matches or surpasses baselines across inverse problems and reward-guided generation with \textbf{as few as 3 NFEs}, giving at least an order-of-magnitude speedup in comparison to prior state of the art. |
| title | How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.27147 |