mlsanityData to 7 Oct 2026

LayoutFlow: Flow Matching for Layout Generation

arXiv 2403.18187 ↗First posted 27 Mar 2024cs.CVcited by 21

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Finding a suitable layout represents a crucial task for diverse applications in graphic design. Motivated by simpler and smoother sampling trajectories, we explore the use of Flow Matching as an alternative to current diffusion-based layout generation models. Specifically, we propose LayoutFlow, an efficient flow-based model capable of generating high-quality layouts. Instead of progressively denoising the elements of a noisy layout, our method learns to gradually move, or flow, the elements of an initial sample until it reaches its final prediction. In addition, we employ a conditioning scheme that allows us to handle various generation tasks with varying degrees of conditioning with a single model. Empirically, LayoutFlow performs on par with state-of-the-art models while being significantly faster.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 37 of its 49 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

37 of 49 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints7 Feb
  2. 2023LayoutDM: Transformer-based Diffusion Model for Layout Generation4 May
  3. 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models21 Mar
  4. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generation14 Mar
  5. 2023Unifying Layout Generation with a Decoupled Diffusion Model9 Mar
  6. 2023DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer7 Mar
  7. 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusion27 Jan

Other references · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2018Neural Ordinary Differential Equationscited by 3,733
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  10. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  11. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  12. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
18 more
  1. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  2. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  3. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  4. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  5. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 130
  6. 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 122
  7. 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
  8. 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 93
  9. 2021Variational Transformer Networks for Layout Generationcited by 88
  10. 2019Neural Design Network: Graphic Layout Generation with Constraintscited by 83
  11. 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
  12. 2020Attribute-conditioned Layout GAN for Automatic Graphic Designcited by 67
  13. 2023PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layoutcited by 60
  14. 2023LayoutPrompter: Awaken the Design Ability of Large Language Modelscited by 47
  15. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  16. 2023Diffusion-based Document Layout Generationcited by 21
  17. 2023LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Modelscited by 17
  18. 2023Unsupervised Domain Adaption with Pixel-level Discriminator for Image-aware Layout Generationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 11; 2026: 7.

21 papers.

Sort:

By area:

  1. 2024CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generationcited by 58
  2. 2025ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generationcited by 37
  3. 2024VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correctioncited by 14
  4. 2025Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluationcited by 13
  5. 2025Hadamard product in deep learning: Introduction, Advances and Challengescited by 9
  6. 2025EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observationscited by 5
  7. 2025B'ezierFlow: Learning B'ezier Stochastic Interpolant Schedulers for Few-Step Generationcited by 5
  8. 2026APEX: Academic Poster Editing Agentic Expertcited by 5
  9. 2025FlowRec: Prior-Informed Flow Matching for Efficient Sequential Recommendation Generationcited by 4
  10. 2026Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligencecited by 4
  11. 2025LayoutRAG: Retrieval-Augmented Model for Content-agnostic Conditional Layout Generationcited by 3
  12. 2025Agentic Design Review Systemcited by 2
9 more
  1. 2025OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learningcited by 2
  2. 2024SLayR: Scene Layout Generation with Rectified Flowcited by 1
  3. 2025Interleaved Gibbs Diffusion: Generating Discrete-Continuous Data with Implicit Constraintscited by 1
  4. 2026PSDesigner: Automated Graphic Design with a Human-Like Creative Workflowcited by 1
  5. 2025UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generationcited by 0
  6. 2026Native Extrapolation Awareness in Flow-Based Conditional Generationcited by 0
  7. 2026Towards Design Compositingcited by 0
  8. 2026Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design Templatescited by 0
  9. 2026Model-Aware Schedules Improve Generation via Fiberwise Optimal Transportcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LayoutDiT: Exploring Content-Graphic Balance in Layout Generation with Diffusion Transformer
  2. 2024Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Model
  3. 2026FlowPlace: Flow Matching for Chip Placement
  4. 2023DiffPattern: Layout Pattern Generation via Discrete Diffusion
  5. 2025DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion
  6. 2024DogLayout: Denoising Diffusion GAN for Discrete and Continuous Layout Generation
  7. 2026Hierarchical Discrete Flow Matching for Graph Generation
  8. 2024CoLay: Controllable Layout Generation through Multi-conditional Latent Diffusion