# MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs

arXiv: https://arxiv.org/abs/2608.28669 · HTML: https://mlsanity.com/paper/2608.28669/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 53 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [SolidGen: An Autoregressive Model for Direct B-rep Synthesis](https://mlsanity.com/paper/2203.13944/) (2022)
- [Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models](https://mlsanity.com/paper/2501.19054/) (2025)
- [GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priors](https://mlsanity.com/paper/2409.16294/) (2024)
- [CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design](https://mlsanity.com/paper/2507.09792/) (2025)
- [cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning](https://mlsanity.com/paper/2505.22914/) (2025)
- [HistCAD: Constraint-Aware Parametric CAD Histories for Evaluating Editability](https://mlsanity.com/paper/2602.19171/) (2025)
- [FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories](https://mlsanity.com/paper/2606.17696/) (2026)

## Abstract (arXiv)

Recovering an executable parametric CAD program from an observed object is fundamentally ambiguous, because the same final geometry can result from different construction procedures. We study this problem from four types of input: natural-language descriptions, rendered images, point clouds, and STEP/B-Rep geometry. MIRAGE-CAD maps each input to a shared construction representation and mediates program generation through an explicit construction-plan interface. The resulting Python CAD code is executed by an OpenCASCADE kernel to build the solid and export it as STEP. On 2,500 held-out queries per modality, the system achieves 55.4-70.0% build success and 52.3-66.2% STEP export success without retrieval at inference. Controlled comparisons show that strong reconstruction does not depend on expressing the construction representation as text: a decoder conditioned directly on the continuous representation also reconstructs strongly, while an exposure-matched plan-based decoder shows no detected material loss in per-part geometric fidelity. The explicit plan instead provides a readable and separately measurable intermediate representation whose agreement with the reference construction is informative about downstream execution success. Finally, we show that executable validity, geometric fidelity, and parametric responsiveness can diverge substantially and should therefore be evaluated separately.