AI Paper Atlas

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

LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer

Yuzhuo Chen, Zehua Ma, Jianhua Wang, Kai Kang, Shunyu Yao, Weiming Zhang

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 4 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 Group Isolation Attention (ablation)LAMIC · XVerseBench-extended (two-reference)ID-S: 39.15 -> 78.04Improved
add Group Isolation Attention (ablation)LAMIC · XVerseBench-extended (four-reference)IN-R: 66.95 -> 89.81Improved
add Region-Modulated Attention (ablation)LAMIC · XVerseBench-extended (two-reference)IN-R: 81.77 -> 92.39Improved
add Region-Modulated Attention (ablation)LAMIC · XVerseBench-extended (three-reference)IN-R: 87.45 -> 91.90Improved
add Region-Modulated Attention (ablation)LAMIC · XVerseBench-extended (two-reference)AES: 54.91 -> 53.59Hurt
add Region-Modulated Attention (ablation)LAMIC · XVerseBench-extended (four-reference)ID-S: 65.81 -> 70.25Improved
raise first-stage step ratio from 0.05 to 0.20 (ablation)LAMIC · XVerseBench-extended (two-reference)IN-R: 92.39 -> 95.26Improved
raise first-stage step ratio from 0.05 to 0.20 (ablation)LAMIC · XVerseBench-extended (two-reference)AES: 53.59 -> 51.90Hurt
raise first-stage step ratio from 0.05 to 0.20 (ablation)LAMIC · XVerseBench-extended (three-reference)DPG: 91.95 -> 86.48Hurt
raise first-stage step ratio from 0.05 to 0.20 (ablation)LAMIC · XVerseBench-extended (four-reference)FI-R: 20.81 -> 20.71No clear effect
use LAMIC vs layout-unaware baselines for FI-Rmulti-reference composition · XVerseBench-extended (four-reference)FI-R: 23.71 -> 20.81No clear effect
LAMIC vs UNO on aestheticsmulti-reference composition · XVerseBench-extended (two-reference)AES: 59.52 -> 53.59Hurt

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