AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model

Anirud Aggarwal, Abhinav Shrivastava, Matthew Gwilliam

ICLR 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
use 100 calibration prompts instead of 33 (ablation)ECAD PixArt-alpha · Calibration Image RewardImage Reward: 0.85 -> 0.94Improved
use population size 72 instead of 24 (ablation)ECAD PixArt-alpha · Latency of highest-TMACs schedulems / img: 122.96 -> 100.68Improved
generate 10 images per prompt instead of 3 (ablation)ECAD PixArt-alpha · Calibration Image RewardImage Reward: 0.96 -> 0.94No clear effect
allow direct copies of parents instead of crossover probability 1.0 (ablation)ECAD PixArt-alpha · MJHQ-30KFID: 9.64 -> 8.60Improved
use 4-point crossover instead of 1-point crossover (ablation)ECAD PixArt-alpha · Latencyms / img: 114.78 -> 100.30Improved
use mutation probability 5% instead of 1% (ablation)ECAD PixArt-alpha · MJHQ-30KFID: 9.11 -> 8.60Improved
use mutation probability 5% instead of 15% (ablation)ECAD PixArt-alpha · Latencyms / img: 127.83 -> 100.30Improved
calibrate on ChatGPT-generated prompts instead of Image Reward Benchmark (ablation)ECAD PixArt-alpha · MJHQ-30KFID: 8.18 -> 8.05No clear effect
calibrate on 100 painted-landscape prompts instead of Image Reward Benchmark (ablation)ECAD PixArt-alpha · MJHQ-30KFID: 8.18 -> 8.55No clear effect
calibrate on 5-word prompts instead of Image Reward Benchmark (ablation)ECAD PixArt-alpha · MJHQ-30KFID: 8.18 -> 7.42No clear effect
calibrate on 10 prompts instead of 100 (ablation)ECAD PixArt-alpha · MJHQ-30KFID: 8.18 -> 10.02Hurt
run 50 more generations on PixArt-Sigma after transfer from PixArt-alpha (ablation)ECAD · PixArt-Sigma speedupspeedup: 1.62x -> 1.98xImproved

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