# 递归流匹配

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-26 08:00
- AIHOT 分数：68
- AIHOT 链接：https://aihot.virxact.com/items/cmpnfrc8n0x7csl01b3yfc2jx
- 原文链接：https://arxiv.org/abs/2605.26535

## AI 摘要

递归流匹配（RecFM）是一种用于预测复杂时空动态的生成式框架。该模型通过强制自一致性来对齐跨离散化尺度的轨迹，从而减少离散化误差并提升物理任务的各项性能。据称，这是首个能够为科学系统实现高保真度一步与少步（2-4步）动态生成的方法，其性能可与最先进的多步求解器相媲美。在多个科学基准测试中，RecFM 实现了最高 20 倍于领先扩散模型的速度提升，同时提高了预测精度。与基础流匹配相比，其均方误差降低了超过 15%。

## 正文

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.