AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion

Yueming Pan, Ruoyu Feng, Qi Dai, Yuqi Wang, Wenfeng Lin, Mingyu Guo, Chong Luo, Nanning Zheng

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 13 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 REPA (ablation)LightningDiT-XL · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 8.17 -> 7.08Improved
add SemVAE semantic latents (ablation)LightningDiT-XL+REPA · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 7.08 -> 5.24Improved
add semantic-first asynchronous denoising (ablation)LightningDiT-XL+REPA+SemVAE · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 5.24 -> 3.03Improved
use SemVAE instead of PCA compression (ablation)SFD · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 4.06 -> 3.03Improved
add semantic-first mechanism (ablation)ReDi · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 5.33 -> 4.41Improved
add SFD (ablation)VA-VAE · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 4.52 -> 4.14Improved
use SD-VAE texture latent instead of VA-VAE (ablation)SFD · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 4.14 -> 3.03Improved
temporal offset 0.3 instead of 0 (joint denoising) (ablation)SFD · ImageNet 256x256 (400K iter)FID: 3.03Improved
increase offset beyond 0.3 up to 1.0 (ablation)SFD · ImageNet 256x256 (400K iter)FIDHurt
DINOv2-B target instead of MAE-B (ablation)SemVAE · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 6.29 -> 3.03Improved
scale target encoder from DINOv2-B to DINOv2-L (ablation)SemVAE · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 3.03 -> 2.97Improved
increase semantic channels from 2 to 16 (ablation)SemVAE · ImageNet 256x256 (ablation, LightningDiT-XL 400K)FID: 3.90 -> 3.03Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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