AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Improving Classifier-Free Guidance of Flow Matching via Manifold Projection

Jian-Feng Cai, Haixia Liu, Zhengyi Su, Chao Wang

ICML 2026 · Image generation › Fast diffusion sampling · approach: Guidance and alignment for flow matching · 0 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
add manifold projection (CFG-MP+) on top of flow-matching CFGDiT-XL-2-256 CFG(D2F) · ImageNet 256, w=2.0, NFE=120IS: 71.48 -> 86.26Improved
add manifold projection to CFGDiT-XL-2-256 CFG(D2F) · ImageNet 256, w=1.5, NFE=120FID: 7.45 -> 7.77 (CFG-MP), 7.91 (CFG-MP+)No clear effect
add manifold projection to CFGDiT-XL-2-256 CFG(D2F) · ImageNet 256, w=2.5, NFE=60FID: 12.85 -> 12.51 (CFG-MP), 12.30 (CFG-MP+)Improved
add manifold projection (CFG-MP/MP+) to CFGFlux-dev · DrawBench, w=3, NFE=120HPSv2: 29.30 -> 30.18 (MP), 30.79 (MP+)Improved
add manifold projection (CFG-MP/MP+) to CFGSD3.5 · GenEval overalloverall accuracy (%): 58.36 -> 60.81 (MP), 61.41 (MP+)Improved
add manifold projection to CFGSD3.5 · Pick-a-Pic, ImageReward, small metric gaps (w=3.0, NFE=60)Pick score: 22.32 -> 22.35 (MP), 22.47 (MP+)No clear effect
use Anderson Acceleration AA(1,1) for the projection fixed-point iteration (ablation)CFG-MP on DiT-XL-2-256 · prediction-gap relative changerelative change rImproved
use operator G (unconditional step first) instead of H (ablation)CFG-MP fixed-point iteration · DiT-XL-2-256, K=6relative change r: FPI(G) -6% to -5% vs FPI(H) -4% to -2%Improved
increase FPI iterations K per step (ablation)CFG-MP+ on SD3.5 · HPSv2 / ImageRewardHPSv2Improved
increase AA window size from 1 to 3 (ablation)CFG-MP+ with operator G · HPSv2 and IRHPSv2, ImageRewardImproved
vary AA damping factor beta (0.1 to 1) (ablation)CFG-MP+ · HPSv2 / IRHPSv2, ImageRewardMixed
vary AA window m and damping beta (m=1, beta=1.0 vs others) (ablation)CFG-MP+ on DiT-XL-2-256 · relative prediction-gap reduction, K=3-r (%): 9.31 (m=1, beta=0.2) -> 9.44 (m=1, beta=1.0)No clear effect

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