# VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction

arXiv: https://arxiv.org/abs/2412.04237 · HTML: https://mlsanity.com/paper/2412.04237/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 69 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [Visual Prompting via Image Inpainting](https://mlsanity.com/paper/2209.00647/) (2022)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [What Makes Good Examples for Visual In-Context Learning?](https://mlsanity.com/paper/2301.13670/) (2023)
- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://mlsanity.com/paper/2202.07206/) (2022)
- [LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators](https://mlsanity.com/paper/1901.06767/) (2019)
- [LayoutTransformer: Layout Generation and Completion with Self-attention](https://mlsanity.com/paper/2006.14615/) (2020)
- [LayoutVAE: Stochastic Scene Layout Generation From a Label Set](https://mlsanity.com/paper/1907.10719/) (2019)
- [Self-correcting LLM-controlled Diffusion Models](https://mlsanity.com/paper/2311.16090/) (2023)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [CanvasVAE: Learning to Generate Vector Graphic Documents](https://mlsanity.com/paper/2108.01249/) (2021)
- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model](https://mlsanity.com/paper/2204.13509/) (2022)

## Built on by (most cited first, 15 of 15)

- [PreGenie: An Agentic Framework for High-quality Visual Presentation Generation](https://mlsanity.com/paper/2505.21660/) (2025)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design](https://mlsanity.com/paper/2506.21934/) (2025)
- [Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement](https://mlsanity.com/paper/2603.22187/) (2026)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [E-InMeMo: Enhanced Prompting for Visual In-Context Learning](https://mlsanity.com/paper/2504.18158/) (2025)
- [SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection](https://mlsanity.com/paper/2509.07473/) (2025)
- [PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning](https://mlsanity.com/paper/2509.21926/) (2025)
- [PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation](https://mlsanity.com/paper/2603.24078/) (2026)
- [PRISM: Learning Design Knowledge from Data for Stylistic Design Improvement](https://mlsanity.com/paper/2601.11747/) (2026)
- [Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs](https://mlsanity.com/paper/2606.00592/) (2026)
- [ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation](https://mlsanity.com/paper/2608.24103/) (2026)
- [SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts](https://mlsanity.com/paper/2609.03109/) (2026)
- [Rethinking Camouflage Image Generation towards a Training-Free Paradigm](https://mlsanity.com/paper/2609.14377/) (2026)
- [PLAYGROUND: Progressive Layout Generation with Render-Grounded Planning](https://mlsanity.com/paper/2610.18865/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have proven effective for layout generation due to their ability to produce structure-description languages, such as HTML or JSON. In this paper, we argue that while LLMs can perform reasonably well in certain cases, their intrinsic limitation of not being able to perceive images restricts their effectiveness in tasks requiring visual content, e.g., content-aware layout generation. Therefore, we explore whether large vision-language models (LVLMs) can be applied to content-aware layout generation. To this end, inspired by the iterative revision and heuristic evaluation workflow of designers, we propose the training-free Visual-Aware Self-Correction LAyout GeneRation (VASCAR). VASCAR enables LVLMs (e.g., GPT-4o and Gemini) iteratively refine their outputs with reference to rendered layout images, which are visualized as colored bounding boxes on poster background (i.e., canvas). Extensive experiments and user study demonstrate VASCAR's effectiveness, achieving state-of-the-art (SOTA) layout generation quality. Furthermore, the generalizability of VASCAR across GPT-4o and Gemini demonstrates its versatility.