AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation

Youngwoo Shin, Jiwan Hur, Junmo Kim

ICLR 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 SSG guidanceVAR-d30 · ImageNet 256x256FID: 2.02 -> 1.68Improved
add SSG guidanceVAR-d16 · ImageNet 256x256FID: 3.42 -> 3.27Improved
add SSG guidanceVAR-d36 · ImageNet 512x512FID: 2.70 -> 2.39Improved
add SSG guidanceHART-0.7B · MJHQ-30KFID: 8.46 -> 7.28Improved
add SSG guidanceInfinity-2B · MJHQ-30KFID: 10.01 -> 9.68Improved
add SSG guidanceVAR-d30 · ImageNet 256x256precision: 0.82 -> 0.81No clear effect
add SSG guidanceVQ-Diffusion (adapted) · ImageNet 256x256FID: 9.39 -> 9.18Improved
use DSE frequency prior instead of nearest-neighbor spatial prior (ablation)SSG on VAR-d16 · ImageNet 256x256FID: 4.02 -> 3.27Improved
use DSE frequency prior instead of linear spatial prior (ablation)SSG on VAR-d16 · ImageNet 256x256FID: 3.79 -> 3.27Improved
extrapolate high frequencies from interpolated logits instead of zero padding in DSE (ablation)SSG on VAR-d16 · ImageNet 256x256FID: 3.34 -> 3.27Improved
add linear beta_k decay instead of static beta_k (ablation)SSG on VAR-d16 · ImageNet 256x256FID: 3.63 -> 3.27Improved
add linear beta_k decay instead of static beta_k (ablation)SSG on VAR-d16 · ImageNet 256x256IS: 287.8 -> 285.3Hurt

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