AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Flow Map Learning via Games

Mark Goldstein, Anshuk Uppal, Raghav Singhal, Aahlad Manas Puli, Rajesh Ranganath

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Guidance and alignment for flow matching

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
replace MeanFlow loss with SGFlow lossflow map model · CIFAR-10 unconditional (10 sampling steps, 200k training steps)FID: 37.32 -> 12.26Improved
replace MeanFlow loss with SGFlow lossflow map model · CIFAR-10 unconditional (50 sampling steps, 200k training steps)FID: 4.54 -> 2.88Improved
replace MeanFlow loss with SGFlow lossflow map model · CIFAR-10 unconditional (100 sampling steps, 200k training steps)FID: 4.23 -> 2.81Improved
replace flow matching with SGFlowfew-step sampling · CIFAR-10 unconditional (10 sampling steps, 200k training steps)FID: 24.87 -> 12.26Improved
replace flow matching with SGFlowmany-step sampling · CIFAR-10 unconditional (100 sampling steps, 200k training steps)FID: 3.05 -> 2.81Improved
replace Lagrangian map matching loss with SGFlowflow map model · CIFAR-10 unconditional (10 sampling steps, 200k training steps)FID: 248.76 -> 12.26Improved
replace Eulerian map matching loss with SGFlowflow map model · CIFAR-10 unconditional (100 sampling steps, 200k training steps)FID: 38.95 -> 2.81Improved
replace Progressive map matching loss with SGFlowflow map model · CIFAR-10 unconditional (50 sampling steps, 200k training steps)FID: 235.20 -> 2.88Improved
replace MeanFlow with SGFlowflow map model · CIFAR-10 U-Net backward passpeak GPU memory (Gb): 14.2 -> 43.2Hurt
replace Lagrange loss with SGFlowflow map model · CIFAR-10 U-Net backward passpeak GPU memory (Gb): 69.8 -> 43.2Improved

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