AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts

Nuoyan Zhou, Zhijun Tu, Lei Yu, Kun Cheng, jie hu, Nannan Wang, Xinghao Chen

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 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
add scale-aware token-routed MoE (STMoE) (ablation)VAR-d16 · ImageNet 256 (VAR-d16, 100 epochs)FID: 4.10 -> 2.99Improved
add semantic guidance (SG) alignment (ablation)VAR-d16 · ImageNet 256 (VAR-d16, 100 epochs)FID: 4.10 -> 3.59Improved
add semantic guidance on top of STMoE (ablation)VAR-d16 + STMoE · ImageNet 256 (VAR-d16, 100 epochs)FID: 2.99 -> 2.65Improved
add STMoE on top of semantic guidance (ablation)VAR-d16 + SG · ImageNet 256 (VAR-d16, 100 epochs)FID: 3.59 -> 2.65Improved
use token-routed STMoE instead of scale-routed SMoE (ablation)VAR-d16 · ImageNet 256 (VAR-d16, 100 epochs)FID: 3.11 -> 2.99Improved
add MoEEC routing (no scale awareness) (ablation)VAR-d16 · ImageNet 256 (VAR-d16, 100 epochs)FID: 4.10 -> 4.06No clear effect
add MoE++ routing (ablation)VAR-d16 · ImageNet 256 (VAR-d16, 100 epochs)FID: 4.10 -> 3.39Improved
use STMoE instead of SMoE for expert load balance (ablation)VAR-d16 · VAR-d16 routed-token loadexpert load variance: 6.62 -> 2.41Improved
align with Mocov3 features (ablation)VAR-d16 · ImageNet 256 (VAR-d16, 100 epochs)FID: 4.10 -> 4.11No clear effect
align with DINOv3 instead of DINOv2 (ablation)VAR-d16 + SG · ImageNet 256 (VAR-d16, 100 epochs)FID: 3.81 -> 3.59Improved
align aggregated intermediate-scale features (SG-M) instead of only the final aggregated feature (SG-Last) (ablation)VAR-d16 + SG · ImageNet 256 (VAR-d16, 100 epochs)FID: 3.81 -> 3.59Improved
train MEPA-d16 for 200 instead of 100 epochsMEPA-d16 · ImageNet 256x256FID: 2.65 -> 2.32Improved

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