AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

StructMAR: Structure-Aware Masked Autoregression for Explicit Layout Alignment in Text-to-Image Generation

Gang Cao, Junying Zhang

ICML 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control

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 layout concatenation to plain MAR (ablation)Plain MAR · COCO-PositionAP: 15.20 -> 22.30Improved
use layout cross-attention instead of concatenation (ablation)MAR · COCO-PositionAP: 22.30 -> 27.60Improved
add soft layout attention bias (ablation)MAR · COCO-PositionAP: 27.60 -> 45.80Improved
make the X->L layout bias binary instead of soft (ablation)MAR · COCO-PositionAP: 45.80 -> 51.00Improved
add 2D RoPE and gated cross-attention to the binary bias model (ablation)StructMAR · COCO-PositionAP: 51.00 -> 52.40Improved
add GRPO fine-tuning (ablation)StructMAR · COCO-PositionAP: 52.40 -> 57.20Improved
add GRPO fine-tuning (ablation)StructMAR · COCO-PositionmIoU: 75.90 -> 79.40Improved
use GroundingDINO as GRPO reward detector instead of Faster R-CNN (ablation)StructMAR · COCO-PositionAP: 57.20 -> 57.68Improved
use YOLOv8 instead of Faster R-CNN as reward detector (ablation)StructMAR · COCO-PositionAP: 57.20 -> 56.14Hurt
add GRPO with Faster R-CNN reward (ablation)StructMAR · COCO-MIGinstance success rate: 58.58 -> 61.70Improved
replace diffusion MIGC with StructMARlayout-to-image generator · COCO-MIG (L2)instance success rate: 67.70 -> 66.15Hurt
replace diffusion MIGC with StructMARlayout-to-image generator · COCO-MIG (L6)instance success rate: 56.88 -> 62.80Improved

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