AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

SCAN: Self-Calibrated AutoregressioN for High-Quality Visual Generation

Zhanzhou Feng, Qingpei Guo, Jingdong Chen, Feng Gao, Ming Yang, Shiliang Zhang

AAAI 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 30 refinement iterations at inference (ablation)SCAN-XL · ImageNet 256x256FID: 2.52 -> 2.10Improved
add 30 refinement iterations at inference (ablation)SCAN-L · ImageNet 256x256FID: 3.05 -> 2.51Improved
add 30 refinement iterations at inference (ablation)SCAN-XXL · ImageNet 256x256FID: 2.24 -> 1.95Improved
increase refinement iterations from 30 to 60 (ablation)SCAN-XL · ImageNet 256x256FID: 2.10 -> 2.03 (latency 3.56 -> 5.11)No clear effect
train with only random-noise negatives (ablation)SCAN-XL · ImageNet 256x256FID (initial generation): 2.52 -> 3.27Hurt
train with only location-permuted negatives (ablation)SCAN-XL · ImageNet 256x256FID (initial generation): 2.52 -> 2.87Hurt
train with only teacher-forcing negatives (ablation)SCAN-XL · ImageNet 256x256FID (with refinement): 2.10 -> 2.31Hurt
combine three negative sample types (ablation)SCAN-XL · ImageNet 256x256FID (with refinement): 2.31 -> 2.10 (vs teacher forcing only)Improved
use SCAN-XL instead of LlamaGen-XLSCAN-XL · ImageNet 256x256latency (s): 19.76 -> 3.56Improved

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