# Neurosymbolic Models for Computer Graphics

arXiv: https://arxiv.org/abs/2304.10320 · HTML: https://mlsanity.com/paper/2304.10320/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2023.

## Built on by (most cited first, 28 of 28)

- [CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM](https://mlsanity.com/paper/2411.04954/) (2024)
- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [Can Large Language Models Understand Symbolic Graphics Programs?](https://mlsanity.com/paper/2408.08313/) (2024)
- [ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives](https://mlsanity.com/paper/2305.05661/) (2023)
- [Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts](https://mlsanity.com/paper/2409.17106/) (2024)
- [BlenderAlchemy: Editing 3D Graphics with Vision-Language Models](https://mlsanity.com/paper/2404.17672/) (2024)
- [DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometry](https://mlsanity.com/paper/2503.13110/) (2025)
- [Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis](https://mlsanity.com/paper/2412.08603/) (2024)
- [CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs](https://mlsanity.com/paper/2311.16703/) (2023)
- [Text-to-3D Shape Generation](https://mlsanity.com/paper/2403.13289/) (2024)
- [Learning to Edit Visual Programs with Self-Supervision](https://mlsanity.com/paper/2406.02383/) (2024)
- [Natural Language Commanding via Program Synthesis](https://mlsanity.com/paper/2306.03460/) (2023)
- [ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points](https://mlsanity.com/paper/2503.02745/) (2025)
- [EvoCAD: Evolutionary CAD Code Generation with Vision Language Models](https://mlsanity.com/paper/2510.11631/) (2025)
- [PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction](https://mlsanity.com/paper/2404.10620/) (2024)
- [FaccAID: A Transformer Model for Neuro-Symbolic Facade Reconstruction](https://mlsanity.com/paper/2406.01829/) (2024)
- [A Survey of Methods for Converting Unstructured Data to CSG Models](https://mlsanity.com/paper/2305.01220/) (2023)
- [Computer-Aided Layout Generation for Building Design: A Review](https://mlsanity.com/paper/2504.09694/) (2025)
- [4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes](https://mlsanity.com/paper/2610.03715/) (2026)
- [Learning to Infer Generative Template Programs for Visual Concepts](https://mlsanity.com/paper/2403.15476/) (2024)
- [Learning to Place Objects with Programs and Iterative Self Training](https://mlsanity.com/paper/2503.04496/) (2025)
- [SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Design](https://mlsanity.com/paper/2603.13098/) (2026)
- [A Neurosymbolic Approach to Adaptive Feature Extraction in SLAM](https://mlsanity.com/paper/2407.06889/) (2024)
- [A Unified Differentiable Boolean Operator with Fuzzy Logic](https://mlsanity.com/paper/2407.10954/) (2024)
- [Mediating Modes of Thought: LLM's for design scripting](https://mlsanity.com/paper/2411.14485/) (2024)
- [Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data](https://mlsanity.com/paper/2508.18244/) (2025)
- [AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer](https://mlsanity.com/paper/2602.12100/) (2026)
- [Flatten The Complex: Joint B-Rep Generation via Compositional k-Cell Particles](https://mlsanity.com/paper/2601.17733/) (2026)

## Abstract (arXiv)

Procedural models (i.e. symbolic programs that output visual data) are a historically-popular method for representing graphics content: vegetation, buildings, textures, etc. They offer many advantages: interpretable design parameters, stochastic variations, high-quality outputs, compact representation, and more. But they also have some limitations, such as the difficulty of authoring a procedural model from scratch. More recently, AI-based methods, and especially neural networks, have become popular for creating graphic content. These techniques allow users to directly specify desired properties of the artifact they want to create (via examples, constraints, or objectives), while a search, optimization, or learning algorithm takes care of the details. However, this ease of use comes at a cost, as it's often hard to interpret or manipulate these representations. In this state-of-the-art report, we summarize research on neurosymbolic models in computer graphics: methods that combine the strengths of both AI and symbolic programs to represent, generate, and manipulate visual data. We survey recent work applying these techniques to represent 2D shapes, 3D shapes, and materials & textures. Along the way, we situate each prior work in a unified design space for neurosymbolic models, which helps reveal underexplored areas and opportunities for future research.