AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE

Haoyou Deng, Keyu Yan, Chaojie Mao, Xiang Wang, Yu Liu, Changxin Gao, Nong Sang

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 1 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
route with predicted clean latent x0 from previous step (saliency-harnessing router) (ablation)DiffMoE-B · ImageNet 256x256 (cfg=1.5)FID50K: 8.03 -> 6.95Improved
add trajectory routing loss (ablation)DiffMoE-B + saliency router · ImageNet 256x256 (cfg=1.5)FID50K: 6.95 -> 6.66Improved
post-train with SharpMoEDiffMoE-L · ImageNet 256x256 (cfg=1.5)FID50K: 3.86 -> 3.10Improved
post-train with SharpMoEEC-DiT-L · ImageNet 256x256 (cfg=1.5)FID50K: 4.09 -> 3.27Improved
post-train with SharpMoE (no routing loss, uniform allocation)TC-DiT-L · ImageNet 256x256 (cfg=1.5)FID50K: 5.07 -> 3.72Improved
post-train with SharpMoEDiffMoE-S · ImageNet 256x256 (cfg=1.0)FID50K: 46.55 -> 45.52Improved
vary rollout steps T from 5 to 20 in full-trajectory training (ablation)SharpMoE · ImageNet 256x256FID50KNo 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