Computer-aided design (CAD) is the digital construction of 2D and 3D objects, and is central to a wide range of engineering and manufacturing applications like automobile and aviation. Despite its importance, CAD modeling remains largely a time-intensive, manual task. Recent works have attempted to automate this process with small transformer-based models and handcrafted CAD sequence representations. However, there has been little effort to leverage the potential of large language models (LLMs) for sequential CAD design. In this work, we introduce a new large-scale dataset of more than 170k CAD models annotated with high-quality, human-like descriptions generated with our pipeline based on GPT-4.1. Using this dataset, we fine-tune powerful code-LLMs to generate CAD sequences represented in a JSON-based format from natural language descriptions, demonstrating the viability and effectiveness of this approach for text-conditioned CAD generation. Because simple metrics often fail to reflect the quality of generated objects, we introduce geometric and topological metrics based on sphericity, mean curvature, and Euler characteristic to provide richer structural insights. Our experiments and ablation studies on both synthetic and human-annotated data demonstrate that CADmium is able to automate CAD design, drastically speeding up the design of new objects. The dataset, code, and fine-tuned models are available online.

翻译：计算机辅助设计（CAD）是二维与三维对象的数字化构建技术，在汽车、航空等众多工程与制造领域具有核心地位。尽管其重要性不言而喻，CAD建模目前仍主要依赖耗时的人工操作。近期研究尝试通过基于小型Transformer的模型及手工构建的CAD序列表示来实现该过程的自动化，然而利用大语言模型（LLM）进行序列化CAD设计的潜力尚未得到充分探索。本研究引入了一个新的大规模数据集，包含超过17万个CAD模型，并辅以基于GPT-4.1的流水线生成的高质量类人描述标注。借助该数据集，我们对高性能代码-LLM进行微调，使其能够根据自然语言描述生成以JSON格式表示的CAD序列，验证了文本条件化CAD生成方法的可行性与有效性。鉴于简单指标常难以反映生成对象的质量，我们引入了基于球形度、平均曲率与欧拉特征的几何与拓扑度量指标，以提供更丰富的结构洞察。在合成数据与人工标注数据上的实验与消融研究表明，CADmium能够实现CAD设计的自动化，显著加速新对象的创建流程。数据集、代码及微调模型均已公开。