Research map / Image generation / Text-to-image diffusion
PosterLlama: Bridging Design Ability of Langauge Model to Content-Aware Layout Generation
Jaejung Seol, SeoJun Kim, Jaejun Yoo
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 |
|---|---|---|---|
| swap Eva-vit for DINOv2 as visual encoder (with Llama2) (ablation) | PosterLlama · CGL-Dataset | FD: 7.07 -> 3.87 | Improved |
| swap Llama2 for CodeLlama as the language model (ablation) | PosterLlama · CGL-Dataset | FD: 3.87 -> 2.08 | Improved |
| swap Llama2 for CodeLlama as the language model (ablation) | PosterLlama · CGL-Dataset | und_s: 0.9133 -> 0.9905 | Improved |
| add depth-guided poster augmentation on data-scarce PKU (ablation) | PosterLlama · PKU-Dataset | ove: 0.0087 -> 0.0032 | Improved |
| add depth-guided poster augmentation on CGL (ablation) | PosterLlama · CGL-Dataset | FD: 1.43 -> 2.08 | Hurt |
| add depth-guided poster augmentation on CGL (ablation) | PosterLlama · CGL-Dataset | und_s: 0.9987 -> 0.9905 | Hurt |
| add depth-guided poster augmentation on CGL (ablation) | PosterLlama · CGL-Dataset | occ: 0.1476 -> 0.1418 | Improved |
| add depth-guided poster augmentation on PKU (ablation) | PosterLlama · PKU-Dataset | und_s: 0.9661 -> 0.9910 | Improved |
| frozen visual encoder (PosterLlama) versus trained visual encoder (RADM) on inpainting artifacts | PosterLlama vs RADM · CGL-Dataset | FD / occ / rea | Mixed |
| evaluate on augmented leakage-free test samples | RADM · CGL-v2 augmented test | layout metrics | Hurt |
Closest papers by meaning
- PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation (CVPR 2025 · similarity 0.92)
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.89)
- LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models (ICLR 2024 · similarity 0.88)
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints (ICLR 2024 · similarity 0.88)
- Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement (CVPR 2026 · similarity 0.87)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.86)
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.
