Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek

Researchers introduced Seek-CAD, a new system that uses the open-source DeepSeek-R1 language model to generate 3D CAD models locally without requiring expensive cloud-based AI services. The system incorporates visual feedback and self-refinement mechanisms to improve CAD model generation, potentially making AI-assisted design more accessible for industrial applications.

• →Seek-CAD is the first system to use locally deployed open-source LLM DeepSeek-R1 for CAD parametric model generation.
• →The system combines visual feedback and Chain-of-Thought reasoning for self-refinement of generated CAD models.
• →This approach offers a cost-effective alternative to expensive closed-source LLMs for industrial design applications.
• →Researchers created a new 3D CAD dataset based on the SSR (Sketch, Sketch-based feature, and Refinements) paradigm.
• →The training-free methodology provides enhanced flexibility and efficiency compared to traditional fine-tuning approaches.