mlsanityData to 14 Oct 2026

SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

arXiv 2207.04632 ↗First posted 11 Jul 2022cs.CV cs.LGcited by 125

Not on the map. Why?

Abstract (arXiv)

We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-and-extrude modeling operations. Our model utilizes distinct Transformer architectures to encode topological, geometric, and extrusion variations of construction sequences into disentangled codebooks. Autoregressive Transformer decoders generate CAD construction sequences sharing certain properties specified by the codebook vectors. Extensive experiments demonstrate that our disentangled codebook representation generates diverse and high-quality CAD models, enhances user control, and enables efficient exploration of the design space. The code is available at https://samxuxiang.github.io/skexgen.

Key facts. Cited by 125 papers in the map (data through 14 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 11 Jul 2022.

Builds on

27 of 42 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  9. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  10. 2015Pointer Networkscited by 895
  11. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 271
  12. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 269
15 more
  1. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  2. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  3. 2019Write, Execute, Assess: Program Synthesis with a REPLcited by 93
  4. 2021Computer-Aided Design as Languagecited by 82
  5. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 78
  6. 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
  7. 2019Learning to Infer and Execute 3D Shape Programscited by 68
  8. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  9. 2021Vitruvion: A Generative Model of Parametric CAD Sketchescited by 66
  10. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  11. 2021Inferring CAD Modeling Sequences Using Zone Graphscited by 50
  12. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  13. 2020B'ezierSketch: A generative model for scalable vector sketchescited by 43
  14. 2020Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequencescited by 36
  15. 2019Neural Shape Parsers for Constructive Solid Geometrycited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 27; 2025: 36; 2026: 49.

125 papers.

Sort:

By area:

  1. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 103
  2. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 96
  3. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 86
  4. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 81
  5. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 75
  6. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 67
  7. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 66
  8. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 64
  9. 2025Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Modelscited by 47
  10. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  11. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  12. 2025CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generationcited by 43
38 more
  1. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 40
  2. 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
  3. 2024GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priorscited by 38
  4. 2024Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometrycited by 37
  5. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 35
  6. 2025CADCrafter: Generating Computer-Aided Design Models from Unconstrained Imagescited by 35
  7. 2024FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Modelscited by 34
  8. 2024TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Cloudscited by 29
  9. 2024CadVLM: Bridging Language and Vision in the Generation of Parametric CAD Sketchescited by 28
  10. 2025CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Designcited by 25
  11. 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusioncited by 24
  12. 2025Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeekcited by 24
  13. 2023ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitivescited by 23
  14. 2024Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Promptscited by 23
  15. 2022Self-Supervised Representation Learning for CADcited by 22
  16. 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometrycited by 21
  17. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  18. 2025CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editingcited by 19
  19. 2024Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesiscited by 18
  20. 2025Large Language Models for Computer-Aided Design: A Surveycited by 18
  21. 2025AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometrycited by 17
  22. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 16
  23. 2024From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approachcited by 15
  24. 2023Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generationcited by 14
  25. 2024Geometric Deep Learning for Computer-Aided Design: A Surveycited by 14
  26. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 13
  27. 2026Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selectioncited by 11
  28. 2023Improving Unsupervised Visual Program Inference with Code Rewriting Familiescited by 10
  29. 2026IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editingcited by 10
  30. 2025CAD-Coder:Text-Guided CAD Files Code Generationcited by 9
  31. 2025Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawingscited by 9
  32. 2026P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoningcited by 9
  33. 2023PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programscited by 8
  34. 2024NeuroNURBS: Learning Efficient Surface Representations for 3D Solidscited by 8
  35. 2025GenCAD-3D: CAD Program Generation using Multimodal Latent Space Alignment and Synthetic Dataset Balancingcited by 8
  36. 2026ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generationcited by 8
  37. 2026Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Datacited by 8
  38. 2024Learning to Edit Visual Programs with Self-Supervisioncited by 7

50 most cited of 125 All 125 (JSON)