AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties

Jixuan Ying, Haoyu Liu, Timing Yang, Tingyu Zhu, Predrag Neskovic, Anand Bhattad, Cihang Xie, Zeyu Zheng, Alan Yuille, Feng Wang

NeurIPS 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 summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a context-aware generation-order approach for autoregressive image generation to better capture structural dependencies and reasoning properties, as stated in the abstract.

Problem

Autoregressive image generation uses predefined or heuristic generation orders (next-patch, random-order, one-step per scale), which can ignore important structural dependencies in images and limit structural robustness and reasoning.

Approach

Makes the generation order context-aware rather than fixed or heuristic, so the autoregressive model follows image structural dependencies; the abstract does not give further details of the mechanism.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace random order with SAR context-aware order at inferenceMaskGen-XL, Infinity-2B, Infinity-8B · Complex long-prompt benchmarkaverage score (1-5): 2.42 -> 2.92 (MaskGen-XL); 2.92 -> 3.42 (Infinity-8B)Improved
replace random order with SAR orderMaskGen-L, MaskGen-XL, Infinity-2B, Infinity-8B · GenEvalOverall pass rate (%): 56.22 -> 59.99 (MaskGen-XL)Improved
replace random order with SAR orderMaskGen and Infinity models · DPG-BenchOverall (%): 86.09 -> 86.27 (Infinity-8B); 70.11 -> 70.51 (MaskGen-L)Improved
replace random order with SAR orderMaskGen and Infinity models · MJHQ-30KFID: 10.867 -> 10.970 (Infinity-2B); 9.332 -> 9.317 (Infinity-8B)No clear effect
use SAR order instead of sequential order (ablation)MaskGen-XL · GenEvalGenEval score: 0.57 -> 0.58Improved
use SAR order instead of inside-out order (ablation)Infinity-8B · GenEvalGenEval score: 0.808 -> 0.815Improved
use sequential order instead of random (ablation)Infinity-8B · GenEvalGenEval score: 0.804 -> 0.799No clear effect
replace confidence-based position selection with SAR in MaskGIT-Base without retraining (ablation)MaskGIT-Base · ImageNet 256x256 class-conditionalFID: 6.48 -> 5.95Improved
add SAR ranking on top of VAR last-scale decoding (ablation)VAR · VAR inference latency (H100, batch 1)latencyNo clear effect

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