AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Functional Mean Flow in Hilbert Space

Zhiqi Li, Yuchen Sun, Greg Turk, Bo Zhu

CVPR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use x1-prediction instead of u-prediction (ablation)Functional Mean Flow · Navier-Stokesspectrum MSE: 1.2e3 -> 5.6e2Improved
use x1-prediction instead of u-prediction (ablation)Functional Mean Flow · Navier-Stokesdensity MSE: 9.7e-5 -> 8.0e-5Improved
use x1-prediction instead of u-prediction (ablation)Functional Mean Flow · 1D statistical datasetsstatistical MSEs: Genes variance 3.3e-4 -> 2.0e-3; Pop. autocorrelation 7.2e-3 -> 1.1e-4Mixed
use x1-prediction instead of u-prediction (ablation)Functional Mean Flow on MNIST SDF (Functional Diffusion framework) · MNIST SDF training stabilitytraining stability (spatial variance collapse)Improved
replace multi-step functional models with one-step FMFInfty-Diff image generation · CelebA-HQ 64FID_CLIP: 4.57 -> 3.48Improved
replace multi-step functional models with one-step FMFInfty-Diff image generation · LSUN-Church-256FID_CLIP: 10.36 -> 26.57Hurt
use FMF instead of other one-step functional generatorsone-step functional image generation · FFHQ-256FID_CLIP: 24.37 -> 11.37Improved
generate at higher resolution than the training grid (ablation)FMF on CelebA-HQ (trained on 1/4 of 256x256 pixels) · CelebA-HQFID_CLIP: 3.48 (64) -> 10.96 (1024)Hurt
use one-step FMF instead of 64-step Functional DiffusionShapeNet 64-point reconstruction · ShapeNetChamfer: 0.101 -> 0.060 Chamfer; F-Score 0.707 -> 0.584Mixed
use FMF instead of GANO (one-step)Navier-Stokes · Navier-Stokesspectrum MSE: 3.2e4 -> 5.6e2Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy