GeoCAD-LLM: CAD Sequence Generation via Multimodal LLMs with Equivariant Geometric Features🛠️

GeoCAD-LLM_4B🛠️

Base_model: Qwen3-4B-Instruct
Max sequence length: 8,192
Epoch: 2
Learning rate: 1e-4
Batch size: 128
This model specialized for text-to-CAD. However, it also supports multi-modality.

State-of-the-art Performace🏆 in Text2CAD datasets. (as shown in below Tables)
Multimodal CAD Generation🌐: Both text-to-CAD and pc-text-to-CAD.
GeoCAD-LLM directly generate CAD vector sequence as natural language.
Novel Two Stage Training Pipeline🧭: In stage1, training semantic geometry alignment. In stage2, training fine-grained geometry. Especially, we direct levearge E(3)-equivariant features for geomtry-consistent supervision, inherently ensuring geometric feature consistency regardless of input orientation.
Apply Point Cloud Dropout (PCD) technique🧶: PCD mitigates over-reliance on geometric inputs and improves multimodal generalization. Also, it is a critical training technique for multimodal CAD generation.

Please check our paper and supplementary materials.🤗

(TODO)

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support