Research map / Vision-language and multimodal / Multimodal LLMs
PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design
Jiazhe Wei, Ken Li, Tianyu Lao, Haofan Wang, Yueming Lyu, Liang Wang, Caifeng Shan, Chenyang Si
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 |
|---|---|---|---|
| replace standard SFT with perturbed SFT (PSFT) (ablation) | PosterCopilot · Poster layout | IoU: 0.285 -> 0.311 | Improved |
| replace standard SFT with perturbed SFT (PSFT) (ablation) | PosterCopilot · Poster layout | ARD: 0.851 -> 0.699 | Improved |
| add RL-VRA after PSFT (ablation) | PosterCopilot · Poster layout | IoU: 0.311 -> 0.347 | Improved |
| add RL-VRA after PSFT (ablation) | PosterCopilot · Poster layout | ARD: 0.699 -> 0.061 | Improved |
| add RLAF after RL-VRA (ablation) | PosterCopilot · Poster layout | IOPR: 1.72 -> 0.56 | Improved |
| add RLAF after RL-VRA (ablation) | PosterCopilot · Poster layout | IoU: 0.347 -> 0.342 | Hurt |
| add DIoU spatial reward to format reward (ablation) | RL-VRA · Poster layout | IoU: 0.317 -> 0.339 | Improved |
| add aspect-ratio and size reward (ablation) | RL-VRA · Poster layout | ARD: 0.734 -> 0.061 | Improved |
| increase PSFT perturbation sigma beyond 3.0 (ablation) | PSFT · Poster layout | IoU/ARD/IOPR | Hurt |
| increase PSFT sampling number n beyond 5 (ablation) | PSFT · Poster layout | IoU/ARD/IOPR | No clear effect |
Closest papers by meaning
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.88)
- Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement (CVPR 2026 · similarity 0.88)
- Graphic Design with Large Multimodal Model (AAAI 2025 · similarity 0.87)
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints (ICLR 2024 · similarity 0.87)
- Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models (NeurIPS 2026 · similarity 0.87)
- PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation (CVPR 2025 · 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.
