Learn more at:

📝 Paper: arxiv.org/abs/2507.09792
💻 Code: github.com/chandar-lab/...
🤗 Models & Dataset: huggingface.co/collections/...
🌐 Website: chandar-lab.github.io/cadmium-webs...
📋 Blog post: t.co/c3b6U3bIWl

🤖 CADmium annotations don’t just restate JSON-like details!

It produces fluent prompts like “clamp-like ring” that align with how humans describe objects — while still containing the necessary geometric and spatial parameters required for precise physical manipulation.

With human-written prompts, CADmium’s 14B fine-tuned model achieves:

⬆️ Higher F1 on lines, circles, extrusions
⬆️ Better Chamfer & curvature metrics
⬆️ Stronger structural similarity
We avoid extensive pre-training, customized embeddings, and other domain-specific strategies.

Compared to previous CAD annotations, CADmium’s expert-level descriptions are:

📈 Shorter, clearer, and more natural-sounding
📈 Richer vocabulary (2× more unique words)
📈 Preferred by humans for readability & accuracy

📊 Plots illustrating better lexical diversity and conciseness!

Highlights:
✅ GPT-4.1 generates concise, expert-level, human-like geometric descriptions of 176k models.
✅ Qwen2.5-Coder (fine-tuned with LoRA) translates them back into CAD sequences in JSON format.
✅ New metrics to evaluate the structural and topological characteristics.

Why this matters? 🤔
CAD is central to engineering & manufacturing, but creating models is slow and manual.
Automating it would speed up design, lower barriers for non-experts, and transform industries like automotive, aviation, and 3D printing.

Computer-Aided Design (CAD) models are built step-by-step with sketches and extrusions. What if we could generate them directly from natural language?

🤖 Meet CADmium - a new dataset and fine-tuning framework for solving the text-to-CAD problem.