AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion

Noam Issachar, Guy Yariv, Sagie Benaim, Yossi Adi, Dani Lischinski, Raanan Fattal

ICML 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 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
make YaRN time-dependent (DY-YaRN)YaRN on FLUX · DrawBench 4096x4096ImageReward: -0.34 -> 0.15Improved
make YaRN time-dependent (DY-YaRN)YaRN on FLUX · Aesthetic-4K 4096x4096FID: 192.19 -> 186.00Improved
make NTK-aware time-dependent (DY-NTK)NTK on FLUX · DrawBench 4096x4096ImageReward: -1.88 -> -1.22Improved
make NTK-aware time-dependent (DY-NTK)NTK on FLUX · Aesthetic-4K 4096x4096FID: 203.85 -> 183.72Improved
make YaRN time-dependent at low resolutionYaRN on FLUX · Aesthetic-4K 2048x3072FID: 179.54 -> 179.51No clear effect
use DY-NTK instead of time-aware scaled RoPE (TASR)TASR on FLUX · Aesthetic-4K 4096x4096FID: 221.39 -> 183.72Improved
apply DY-YaRN at 6144x6144DY-YaRN on FLUX · resolution scaling, ImageRewardImageRewardHurt
make YaRN time-dependent (DY-YaRN)YaRN on FiTv2-XL/2 · ImageNet 384x384FID: 22.63 -> 21.75Improved
make PI time-dependent (DY-PI)PI on FiTv2-XL/2 · ImageNet 384x384FID: 118.60 -> 39.56Improved
make NTK time-dependent (DY-NTK)NTK on FiTv2-XL/2 · ImageNet 384x384FID: 36.75 -> 36.04Improved
add HiFlow on top of DY-YaRNDY-YaRN · 4096x4096 non-PE comparisonFID: 186.00 -> 169.46Improved
add HiFlow on top of DY-YaRNDY-YaRN · 4096x4096 non-PE comparisonpatch-FID: 78.33 -> 79.64No clear effect

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