AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis

Zhuokun Chen, Jugang Fan, Zhuowei Yu, Bohan Zhuang, Mingkui Tan

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 10 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
apply SparseVAR (tau=0.7) to Infinity-2BInfinity-2B · GenEvallatency (s) and overall score: latency 2.78 -> 1.36; overall 0.7260 -> 0.7209Improved
apply SparseVAR (tau=0.6) to HART-0.7BHART-0.7B · GenEvallatency (s) and overall score: latency 1.32 -> 0.99; overall 0.5602 -> 0.5606Improved
raise exclusion threshold tau to 0.7 (ablation)SparseVAR on HART-0.7B · GenEvaloverall score: 0.5606 -> 0.5119Hurt
raise exclusion threshold tau to 0.7 (ablation)SparseVAR on HART-0.7B · ImageRewardscore: 0.8121 -> 0.4333Hurt
apply SparseVAR (tau=0.7) to Infinity-2BInfinity-2B · HPSv2.1overall score: 30.36 -> 29.89; latency 2.61 -> 1.32Mixed
add anchor tokens (retain a grid of tokens, alpha=4) (ablation)SparseVAR · GenEval (HART, Infinity)generation qualityImproved
start exclusion at a smaller stage P (ablation)SparseVAR · GenEvalquality and latencyHurt
use MSE change of block 16 instead of other blocks or logits similarity (ablation)SparseVAR · GenEval (Infinity, tau=0.6)generation qualityImproved
apply SparseVAR to non-residual FlexVARFlexVAR · ImageNet 512x512FID and latency: FID 4.33 -> 4.38; latency 0.52 -> 0.43Mixed
use token merging or selection (ToMe, PiToMe, SparseViT, ZipVL) instead of SparseVAR (ablation)HART-0.7B · GenEvalquality vs sparsityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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