# DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model

arXiv: https://arxiv.org/abs/2609.35242 · HTML: https://mlsanity.com/paper/2609.35242/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 67 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [FIGR: Few-shot Image Generation with Reptile](https://mlsanity.com/paper/1901.02199/) (2019)
- [Text2CAD: Text to 3D CAD Generation via Technical Drawings](https://mlsanity.com/paper/2411.06206/) (2024)
- [Photo2CAD: Automated 3D solid reconstruction from 2D drawings using OpenCV](https://mlsanity.com/paper/2101.04248/) (2021)
- [DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces](https://mlsanity.com/paper/2603.05607/) (2026)
- [HiDiGen: Hierarchical Diffusion for B-Rep Generation with Explicit Topological Constraints](https://mlsanity.com/paper/2604.02847/) (2026)

## Abstract (arXiv)

Scalable Vector Graphics (SVG) are essential for modern industrial Computer-Aided Design (CAD). However, existing autoregressive SVG generation models are predominantly tailored for artistic creation and struggle to maintain the rigorous geometric fidelity and cross-view spatial alignment required for engineering drawings. To bridge this gap, we introduce DrawingsDreamer, a unified Large Language Model (LLM)-driven framework for multi-view vector-based engineering drawings generation. By formulating the generation of multi-view engineering drawings purely as a sequence modeling task, we eliminate the need of raster image encoders. We propose a Streamlined Representation utilizing hierarchical postfix tokenization, which guides the model to establish local geometric coordinates before assigning semantic boundaries. Optimized via a progressive task-aware curriculum schedule, DrawingsDreamer effectively transitions from localized structural repair to macroscopic generation in a unified model. Extensive experiments demonstrate that our unified model achieves strong performance in both geometric fidelity and syntactic accuracy across diverse conditional and unconditional generation tasks.