AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training

Mengmeng Wang, Dengyang Jiang, Liuzhuozheng Li, Yucheng Lin, Guojiang Shen, Xiangjie Kong, Yong Liu, Guang Dai, Jingdong Wang

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 8 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 SRA 2 VAE-feature alignmentSiT-B/2 · ImageNet 256x256 (no CFG, 400K iters)FID: 33.02 -> 28.89Improved
move alignment from layer 2 to layer 8 (ablation)SRA 2 on SiT-B/2 · ImageNet 256x256 (no CFG, 400K iters)FID: 28.89 -> 36.20Hurt
align over full timestep range instead of [0, 0.5] (ablation)SRA 2 · ImageNet 256x256 (no CFG, 400K iters)FID: 30.04 -> 28.89Improved
align over full timestep range instead of [0.5, 1] (ablation)SRA 2 · ImageNet 256x256 (no CFG, 400K iters)FID: 29.59 -> 28.89Improved
use smooth-l1 instead of l1 (ablation)SRA 2 · ImageNet 256x256 (no CFG, 400K iters)FID: 29.50 -> 28.89Improved
use smooth-l1 instead of l2 (ablation)SRA 2 · ImageNet 256x256 (no CFG, 400K iters)FID: 29.40 -> 28.89Improved
use lambda 1.0 instead of 0.1 (ablation)SRA 2 · ImageNet 256x256 (no CFG, 400K iters)FID: 30.10 -> 28.89Improved
use 5-layer instead of 2-layer MLP head (ablation)SRA 2 · ImageNet 256x256 (no CFG, 400K iters)FID: 31.32 -> 28.89Improved
add SRA 2 to SiT-L/2SiT-L/2 · ImageNet 256x256 (no CFG, 400K iters)FID: 18.8 -> 14.3Improved
add SRA 2 to SiT-XL/2 (1M vs 7M iterations)SiT-XL/2 · ImageNet 256x256 (no CFG)FID: 8.3 -> 8.2Improved
add SRA 2 to REPA at 100K, 200K, 400K iterationsSiT-XL/2+REPA · ImageNet 256x256 (no CFG)FID: FID reductions of 3.1, 1.9, and 1.1Improved
add SRA 2 to VAVAESiT-XL/2+VAVAE · ImageNet 256x256 (no CFG, 400K iters)FID: 4.9 -> 4.4Improved

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