AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DIFFSPARSE: ACCELERATING DIFFUSION TRANSFORMERS WITH LEARNED TOKEN SPARSITY

Haowei Zhu, Ji Liu, Ziqiong Liu, Dong Li, Jun-Hai Yong, Bin Wang, Emad Barsoum

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 3 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 two-stage training instead of single-stage (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 27.40 -> 26.91Improved
use attention-based token importance instead of norm (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 28.89 -> 26.91Improved
use attention-based importance instead of similarity (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 28.07 -> 26.91Improved
add DiffSparse allocation on norm-based ranking (ablation)ToCa-style caching · MS-COCO PixArt-alphaFID-30k: 29.05 -> 28.89 (-0.16)Improved
add DiffSparse allocation on attention-based ranking (ablation)ToCa-style caching · MS-COCO PixArt-alphaFID-30k: 28.35 -> 26.91 (-1.44)Improved
use LPIPS loss instead of L2 (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 27.68 -> 26.91Improved
use LPIPS loss instead of SSIM (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 27.46 -> 26.91Improved
use sparsity interval 0.25 instead of 0.125 (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 27.91 -> 26.91Improved
use sparsity interval 0.25 instead of 1.0 (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 28.22 -> 26.91Improved
add warm-start delta=10 instead of delta=0 (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 27.40 -> 26.91Improved
increase warm-start delta from 10 to 20 (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 26.91 -> 26.95No clear effect
add differentiable learning instead of genetic algorithm search (ablation)DiffSparse · MS-COCO PixArt-alphaFID-30k: 27.94 -> 26.91Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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