AI Paper Atlas

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

Flow Straight and Fast in Hilbert Space: Functional Rectified Flow

Jianxin Zhang, Clayton Scott

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 5 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 functional rectified flow instead of FDP with INR backboneINR on MNIST · MNIST 32x32FID: 0.43 -> 0.41Improved
use functional rectified flow instead of FDP with Vision Transformer backboneVision Transformer on CelebA · CelebA 64x64FID: 11.00 -> 6.63Improved
use functional rectified flow instead of FDP with Vision Transformer backboneVision Transformer on CelebA · CelebA 64x64FID-CLIP: 6.55 -> 3.70Improved
use FRF with a transformer instead of the larger infinity-DIFFCelebA generation · CelebA 64x64FID-CLIP: 4.57 -> 3.70Improved
use FRF with neural operator instead of functional flow matchingNavier-Stokes · Navier-StokesDensity MSE: 4.50 x 10^-5 -> 2.39 x 10^-5Improved

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