AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration

Haowei Zhu, Tingxuan Huang, Xing Wang, Tianyu Zhao, Jiexi Wang, Weifeng Chen, Xurui Peng, Fangmin Chen, Junhai Yong, Bin Wang

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 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
make predictor selection token-adaptive instead of a single global Taylor predictorTaylorSeer · FLUX.1-dev DrawBench (~6.24x)ImageReward: 0.91 -> 0.99Improved
enlarge predictor pool in both distance and order (ablation)TAP · FLUX.1-dev DrawBench (N=7)ImageReward: 0.95 -> 0.99Improved
enlarge either prediction distance or order of the pool (ablation)TAP · FLUX.1-dev DrawBench (N=7)ImageReward: 0.89 -> 0.95Improved
include zeroth-order predictors in the pool (ablation)TAP · FLUX.1-dev DrawBenchImageRewardImproved
shift prediction window left of k instead of right (ablation)TAP · FLUX.1-dev DrawBenchImageRewardImproved
use finer distance step delta=0.1 instead of 1 (ablation)TAP · FLUX.1-dev DrawBenchImageReward: about +0.005No clear effect
use TAP instead of TaylorSeerTAP vs TaylorSeer · Qwen-Image 3.57xPSNR: 18.02 -> 20.13Improved
use TAP instead of TaylorSeerTAP vs TaylorSeer · Qwen-Image 3.57xImageReward: 1.18 -> 1.23Improved
use TAP instead of TaylorSeerTAP vs TaylorSeer · HunyuanVideo VBenchVBench score: 64.89 -> 65.46Improved
push acceleration from N=8 to N=10TAP · FLUX.1-dev DrawBenchImageReward: 0.99 -> 0.91Hurt
use TAP on distilled FLUX-schnellTAP vs TaylorSeer · FLUX.1-schnellPSNR: 22.67 -> 26.26Improved

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