AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion

Giorgos Petsangourakis, Christos Sgouropoulos, Bill Psomas, Theodoros Giannakopoulos, Giorgos Sfikas, Ioannis Kakogeorgiou

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 4 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
replace linear PCA with nonlinear semantic compressor for patch features (ablation)patch-level joint modeling · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 21.4 -> 14.3Improved
add REPA patch-level alignment to linear patch modeling (ablation)ReDi · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 21.4 -> 18.8Improved
add local patch alignment to CLS-only modeling (ablation)CLS-token joint modeling · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 25.7 -> 15.5Improved
align only global CLS features without local alignment (ablation)CLS-token joint modeling · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 25.7 -> 33.7Hurt
add REPA alignment on top of nonlinear patch modeling (ablation)nonlinear local modeling · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 14.3 -> 14.1Improved
add global CLS token and align both local and global (ablation)nonlinear local modeling plus REPA · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 14.1 -> 13.7Improved
aggregate last four DINOv2 layers (9-12) before compression (ablation)nonlinear local modeling · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 14.3 -> 13.3Improved
include shallow layers 3 and 6 in the aggregation (ablation)nonlinear local modeling · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 14.3 -> 16.9Hurt
use multi-layer linear PCA instead of nonlinear compressor (ablation)stacked baseline components · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 17.4 -> 23.1Hurt
add KL regularization to the compressor (ablation)semantic compressor · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 14.3 -> 17.2Hurt
swap DINOv2-B for DINOv3-B (ablation)REGLUE · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 12.9 -> 12.3Improved
swap DINOv2-B for CLIP-L (ablation)REGLUE · ImageNet 256 conditional (SiT-B/2, 400K, no CFG)FID: 12.9 -> 18.1Hurt

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