English

Functional Mean Flow in Hilbert Space

Machine Learning 2025-11-18 v1 Computer Vision and Pattern Recognition

Abstract

We present Functional Mean Flow (FMF) as a one-step generative model defined in infinite-dimensional Hilbert space. FMF extends the one-step Mean Flow framework to functional domains by providing a theoretical formulation for Functional Flow Matching and a practical implementation for efficient training and sampling. We also introduce an x1x_1-prediction variant that improves stability over the original uu-prediction form. The resulting framework is a practical one-step Flow Matching method applicable to a wide range of functional data generation tasks such as time series, images, PDEs, and 3D geometry.

Keywords

Cite

@article{arxiv.2511.12898,
  title  = {Functional Mean Flow in Hilbert Space},
  author = {Zhiqi Li and Yuchen Sun and Greg Turk and Bo Zhu},
  journal= {arXiv preprint arXiv:2511.12898},
  year   = {2025}
}

Comments

29 pages, 13 figures

R2 v1 2026-07-01T07:40:21.621Z