mlsanityData to 7 Oct 2026

BLT: Bidirectional Layout Transformer for Controllable Layout Generation

arXiv 2112.05112 ↗First posted 9 Dec 2021cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Creating visual layouts is a critical step in graphic design. Automatic generation of such layouts is essential for scalable and diverse visual designs. To advance conditional layout generation, we introduce BLT, a bidirectional layout transformer. BLT differs from previous work on transformers in adopting non-autoregressive transformers. In training, BLT learns to predict the masked attributes by attending to surrounding attributes in two directions. During inference, BLT first generates a draft layout from the input and then iteratively refines it into a high-quality layout by masking out low-confident attributes. The masks generated in both training and inference are controlled by a new hierarchical sampling policy. We verify the proposed model on six benchmarks of diverse design tasks. Experimental results demonstrate two benefits compared to the state-of-the-art layout transformer models. First, our model empowers layout transformers to fulfill controllable layout generation. Second, it achieves up to 10x speedup in generating a layout at inference time than the layout transformer baseline. Code is released at https://shawnkx.github.io/blt.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

28 of 50 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  8. 2017Non-Autoregressive Neural Machine Translationcited by 457
  9. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 375
  10. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  11. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 130
  12. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 123
16 more
  1. 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 122
  2. 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
  3. 2020Fully Non-autoregressive Neural Machine Translation: Tricks of the Tradecited by 99
  4. 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 93
  5. 2021Variational Transformer Networks for Layout Generationcited by 88
  6. 2019Neural Design Network: Graphic Layout Generation with Constraintscited by 83
  7. 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
  8. 2020End-to-End Adversarial Text-to-Speechcited by 77
  9. 2018Human-centric Indoor Scene Synthesis Using Stochastic Grammarcited by 73
  10. 2020Attribute-conditioned Layout GAN for Automatic Graphic Designcited by 67
  11. 2019READ: Recursive Autoencoders for Document Layout Generationcited by 51
  12. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  13. 2020Retrieve-Then-Adapt: Example-based Automatic Generation for Proportion-related Infographicscited by 14
  14. 2020Incorporating a Local Translation Mechanism into Non-autoregressive Translationcited by 9
  15. 2021Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenescited by 5
  16. 2021The Layout Generation Algorithm of Graphic Design Based on Transformer-CVAEcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 22; 2024: 21; 2025: 14; 2026: 6.

69 papers.

Sort:

By area:

  1. 2022MAGVIT: Masked Generative Video Transformercited by 341
  2. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  3. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 141
  4. 2023LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generationcited by 92
  5. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 80
  6. 2022Visual Prompt Tuning for Generative Transfer Learningcited by 75
  7. 2023TaleCrafter: Interactive Story Visualization with Multiple Characterscited by 71
  8. 2022Improved Masked Image Generation with Token-Criticcited by 63
  9. 2023LayoutDM: Transformer-based Diffusion Model for Layout Generationcited by 57
  10. 2023LayoutPrompter: Awaken the Design Ability of Large Language Modelscited by 47
  11. 2022LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restrictioncited by 43
  12. 2023Unifying Layout Generation with a Decoupled Diffusion Modelcited by 41
38 more
  1. 2023LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Modelscited by 40
  2. 2024PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLMcited by 39
  3. 2024Graphic Design with Large Multimodal Modelcited by 38
  4. 2025ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generationcited by 37
  5. 2023Relation-Aware Diffusion Model for Controllable Poster Layout Generationcited by 36
  6. 2023Retrieval-Augmented Layout Transformer for Content-Aware Layout Generationcited by 34
  7. 2024PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generationcited by 34
  8. 2023Towards Flexible Multi-modal Document Modelscited by 30
  9. 2024Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraintscited by 26
  10. 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusioncited by 24
  11. 2023Dolfin: Diffusion Layout Transformers without Autoencodercited by 23
  12. 2023CityGen: Infinite and Controllable City Layout Generationcited by 22
  13. 2023DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformercited by 20
  14. 2024Desigen: A Pipeline for Controllable Design Template Generationcited by 19
  15. 2023LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Modelscited by 17
  16. 2022LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designercited by 15
  17. 2023A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptionscited by 15
  18. 2023UI Layout Generation with LLMs Guided by UI Grammarcited by 15
  19. 2023Planning and Rendering: Towards Product Poster Generation with Diffusion Modelscited by 15
  20. 2022COFS: Controllable Furniture layout Synthesiscited by 14
  21. 2024SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posterscited by 14
  22. 2025Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluationcited by 13
  23. 2023VisorGPT: Learning Visual Prior via Generative Pre-Trainingcited by 11
  24. 2023Towards Diverse and Consistent Typography Generationcited by 11
  25. 2024From Elements to Design: A Layered Approach for Automatic Graphic Design Compositioncited by 11
  26. 2024LTSim: Layout Transportation-based Similarity Measure for Evaluating Layout Generationcited by 10
  27. 2025AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Modelscited by 8
  28. 2024Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Modelcited by 7
  29. 2025LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generationcited by 6
  30. 2025Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformerscited by 6
  31. 2025SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Priorcited by 6
  32. 2024Spot the Error: Non-autoregressive Graphic Layout Generation with Wireframe Locatorcited by 5
  33. 2024DocSynthv2: A Practical Autoregressive Modeling for Document Generationcited by 5
  34. 2026AnchoredDream: Zero-Shot 360deg Indoor Scene Generation from a Single View via Geometric Groundingcited by 5
  35. 2024Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Modelscited by 4
  36. 2024Revision Matters: Generative Design Guided by Revision Editscited by 4
  37. 2025PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Designcited by 4
  38. 2026Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligencecited by 4

50 most cited of 69 All 69 (JSON)