| title | Recursive Flow Matching |
|---|---|
| authors | Jiahe Huang, Sihan Xu, Sharvaree Vadgama, Rose Yu |
| date | 2026-05-26 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.26535 |
| upvotes | 17 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving high physical accuracy without incurring high computational cost remains a fundamental challenge, as existing approaches face a critical speed-fidelity trade-off. In this work, we introduce Recursive Flow Matching (RecFM), a generative framework for forecasting complex spatiotemporal dynamics. RecFM enforces self-consistency to align trajectories across discretization scales, reducing discretization errors and improving performance across metrics for physics-based tasks. To our knowledge, this is the first method to achieve high-fidelity one- and few-step (2-4 step) dynamic generation for scientific systems with performance comparable to state-of-the-art multi-step solvers. Across challenging scientific benchmarks, RecFM achieves up to a 20times speedup over leading diffusion-based emulators while improving predictive accuracy. Furthermore, RecFM reduces mean squared error by over 15% compared to vanilla flow matching, offering a scalable and efficient solution for real-time scientific emulation. |
cite
@misc{huang2026recursive,
title={Recursive Flow Matching},
author={Jiahe Huang and Sihan Xu and Sharvaree Vadgama and Rose Yu},
year={2026},
eprint={2605.26535},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.26535}
}