Research map / Large language models / Instruction and fine-tuning
LayoutPrompter: Awaken the Design Ability of Large Language Models
Jiawei Lin, Jiaqi Guo, Shizhao Sun, Zijiang James Yang, Jian-Guang Lou, Dongmei Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| serialize output layout as HTML instead of plain sequence (ablation) | LayoutPrompter · RICO Gen-T | FID: 7.009 -> 3.233 | Improved |
| add dynamic exemplar selection instead of random exemplars (ablation) | LayoutPrompter · RICO Gen-T | FID: 8.154 -> 3.233 | Improved |
| add dynamic exemplar selection instead of random exemplars (ablation) | LayoutPrompter · RICO Gen-R | FID: 14.177 -> 5.178 | Improved |
| add dynamic exemplar selection instead of random exemplars (ablation) | LayoutPrompter · RICO Gen-T | Align.: 0.053 -> 0.109 | Hurt |
| add layout ranker instead of random pick (ablation) | LayoutPrompter · RICO Gen-T | mIoU: 0.367 -> 0.429 | Improved |
| add layout ranker instead of random pick (ablation) | LayoutPrompter · RICO Completion | FID: 11.194 -> 7.318 | Improved |
| add layout ranker instead of random pick (ablation) | LayoutPrompter · RICO Gen-R | Vio. %: 6.54 -> 10.58 | Hurt |
| increase number of exemplars from 1 to 10 (ablation) | LayoutPrompter · RICO Gen-T | FID: 5.007 -> 3.523 | Improved |
| LLM in-context learning vs trained LayoutFormer++ with 500 training samples (ablation) | LayoutPrompter · RICO Gen-T | FID: 92.643 -> 7.201 | Improved |
| LLM in-context learning vs trained LayoutFormer++ with full training set | LayoutPrompter · RICO Gen-TS | FID: 0.757 -> 1.458 | Hurt |
| LayoutPrompter vs DS-GAN on content-aware generation | LayoutPrompter · PosterLayout | Und_s: 0.4320 -> 0.8802 | Improved |
| LayoutPrompter vs parse-then-place on text-to-layout | LayoutPrompter · WebUI | mIoU: 0.6841 -> 0.3190 | Hurt |
Later papers that compared with this method
1 later accepted paper reports LayoutPrompter as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning (CVPR 2026 · better on 5 of 5 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
- LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction (CVPR 2023 · similarity 0.92)
- LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models (ICLR 2024 · similarity 0.91)
- Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement (CVPR 2026 · similarity 0.90)
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.90)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.89)
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints (ICLR 2024 · similarity 0.88)
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.
