# Revision Matters: Generative Design Guided by Revision Edits

arXiv: https://arxiv.org/abs/2406.18559 · HTML: https://mlsanity.com/paper/2406.18559/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 27 May 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Chain of Hindsight Aligns Language Models with Feedback](https://mlsanity.com/paper/2302.02676/) (2023)
- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [LayoutTransformer: Layout Generation and Completion with Self-attention](https://mlsanity.com/paper/2006.14615/) (2020)
- [VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models](https://mlsanity.com/paper/2211.11319/) (2022)
- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)
- [Few-Shot Preference Learning for Human-in-the-Loop RL](https://mlsanity.com/paper/2212.03363/) (2022)
- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [BLT: Bidirectional Layout Transformer for Controllable Layout Generation](https://mlsanity.com/paper/2112.05112/) (2021)
- [Language Reward Modulation for Pretraining Reinforcement Learning](https://mlsanity.com/paper/2308.12270/) (2023)
- [PLay: Parametrically Conditioned Layout Generation using Latent Diffusion](https://mlsanity.com/paper/2301.11529/) (2023)
- [A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions](https://mlsanity.com/paper/2308.12700/) (2023)
- [Leveraging Human Revisions for Improving Text-to-Layout Models](https://mlsanity.com/paper/2405.13026/) (2024)

## Built on by (most cited first, 4 of 4)

- [VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction](https://mlsanity.com/paper/2412.04237/) (2024)
- [SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection](https://mlsanity.com/paper/2509.07473/) (2025)
- [GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework](https://mlsanity.com/paper/2512.00406/) (2025)
- [ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation](https://mlsanity.com/paper/2608.24103/) (2026)

## Abstract (arXiv)

Layout design, such as user interface or graphical layout in general, is fundamentally an iterative revision process. Through revising a design repeatedly, the designer converges on an ideal layout. In this paper, we investigate how revision edits from human designer can benefit a multimodal generative model. To do so, we curate an expert dataset that traces how human designers iteratively edit and improve a layout generation with a prompted language goal. Based on such data, we explore various supervised fine-tuning task setups on top of a Gemini multimodal backbone, a large multimodal model. Our results show that human revision plays a critical role in iterative layout refinement. While being noisy, expert revision edits lead our model to a surprisingly strong design FID score ~10 which is close to human performance (~6). In contrast, self-revisions that fully rely on model's own judgement, lead to an echo chamber that prevents iterative improvement, and sometimes leads to generative degradation. Fortunately, we found that providing human guidance plays at early stage plays a critical role in final generation. In such human-in-the-loop scenario, our work paves the way for iterative design revision based on pre-trained large multimodal models.