paper-with-me

홈 › Papers

Functional Mean Flow in Hilbert Space

2025-11-17 · Zhiqi Li, Yuchen Sun, Greg Turk, Bo Zhu arxiv

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 $x_1$-prediction variant that improves stability over the original $u$-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.

📄 PDF Abstract BibTeX arXiv:2511.12898

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Flow Straight and Fast in Hilbert Space: Functional Rectified Flow

2025-09-12 · Jianxin Zhang, Clayton Scott arxiv

Many generative models originally developed in finite-dimensional Euclidean space have functional generalizations in infinite-dimensional settings. However, the extension of rectified flow to infinite-dimensional spaces …

Generalising maximum mean discrepancy: kernelised functional Bregman divergences

2026-04-27 · Russell Tsuchida, Frank Nielsen arxiv

Bregman divergences play a pivotal role in statistics, machine learning and computational information geometry. Particularly in the context of machine learning, they are central to clustering, exponential families, param…

Optimal-Transport-Guided Functional Flow Matching for Turbulent Field Generation in Hilbert Space

2026-04-07 · Li Kunpeng, Wan Chenguang, Qu Zhisong, Lim Kyungtak 외 arxiv

High-fidelity modeling of turbulent flows requires capturing complex spatiotemporal dynamics and multi-scale intermittency, posing a fundamental challenge for traditional knowledge-based systems. While deep generative mo…

Sequence Modeling with Spectral Mean Flows

2025-10-17 · Jinwoo Kim, Max Beier, Petar Bevanda, Nayun Kim 외 arxiv

A key question in sequence modeling with neural networks is how to represent and learn highly nonlinear and probabilistic state dynamics. Operator theory views such dynamics as linear maps on Hilbert spaces containing me…

Gaussian mixture models in Hilbert spaces via kernel methods

2026-05-07 · Daniel López-Montero, Antonio Álvarez-López, Marcos Matabuena arxiv

Modern datasets across many disciplines increasingly consist of time-evolving, potentially infinite-dimensional random objects, such as dynamic functional data, which are naturally modeled in Hilbert spaces. In these set…