# DesignLab: Designing Slides Through Iterative Detection and Correction

arXiv: https://arxiv.org/abs/2507.17202 · HTML: https://mlsanity.com/paper/2507.17202/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [LayoutTransformer: Layout Generation and Completion with Self-attention](https://mlsanity.com/paper/2006.14615/) (2020)
- [CanvasVAE: Learning to Generate Vector Graphic Documents](https://mlsanity.com/paper/2108.01249/) (2021)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [LayoutDM: Transformer-based Diffusion Model for Layout Generation](https://mlsanity.com/paper/2305.02567/) (2023)
- [D2S: Document-to-Slide Generation Via Query-Based Text Summarization](https://mlsanity.com/paper/2105.03664/) (2021)
- [OpenCOLE: Towards Reproducible Automatic Graphic Design Generation](https://mlsanity.com/paper/2406.08232/) (2024)
- [POSTA: A Go-to Framework for Customized Artistic Poster Generation](https://mlsanity.com/paper/2503.14908/) (2025)
- [Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation](https://mlsanity.com/paper/2311.13602/) (2023)
- [Towards Flexible Multi-modal Document Models](https://mlsanity.com/paper/2303.18248/) (2023)
- [Generating Automatic Feedback on UI Mockups with Large Language Models](https://mlsanity.com/paper/2403.13139/) (2024)
- [CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation](https://mlsanity.com/paper/2506.10890/) (2025)
- [Multimodal Markup Document Models for Graphic Design Completion](https://mlsanity.com/paper/2409.19051/) (2024)
- [UIClip: A Data-driven Model for Assessing User Interface Design](https://mlsanity.com/paper/2404.12500/) (2024)
- [DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation](https://mlsanity.com/paper/2410.00201/) (2024)
- [WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation](https://mlsanity.com/paper/2407.15502/) (2024)

## Built on by (most cited first, 1 of 1)

- [DesignPref: Capturing Personal Preferences in Visual Design Generation](https://mlsanity.com/paper/2511.20513/) (2025)

## Abstract (arXiv)

Designing high-quality presentation slides can be challenging for non-experts due to the complexity involved in navigating various design choices. Numerous automated tools can suggest layouts and color schemes, yet often lack the ability to refine their own output, which is a key aspect in real-world workflows. We propose DesignLab, which separates the design process into two roles, the design reviewer, who identifies design-related issues, and the design contributor who corrects them. This decomposition enables an iterative loop where the reviewer continuously detects issues and the contributor corrects them, allowing a draft to be further polished with each iteration, reaching qualities that were unattainable. We fine-tune large language models for these roles and simulate intermediate drafts by introducing controlled perturbations, enabling the design reviewer learn design errors and the contributor learn how to fix them. Our experiments show that DesignLab outperforms existing design-generation methods, including a commercial tool, by embracing the iterative nature of designing which can result in polished, professional slides.