BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning
This addresses the need for flexible, industry-standard CAD tools, though it appears incremental as it builds on existing LLM and multimodal approaches.
The paper tackles the problem of task-specific models in Computer-Aided Design (CAD) by proposing BrepCoder, a unified multimodal large language model that uses B-rep inputs to perform multiple CAD tasks, achieving superior generalization across tasks.
Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) domain.However, most existing approaches rely on task-specifi c models requiring structural modifi cations for new tasks, and they predominantly focus on point clouds or images rather than the industry-standard Boundary Representation (B-rep) format. To address these limitations, we propose BrepCoder, a unifi ed Multimodal Large Language Model (MLLM) that performs diverse CAD tasks from B-rep inputs. By leveraging the code generation capabilities of Large Language Models (LLMs), we convert CAD modeling sequences into Python-like code and align them with B-rep. We then adopt a two-stage training strategy: First, pre-training on reverse engineering to learn geometric features and design logic. Second, eff ectively extending the model to various downstream tasks such as completion, error correction, and CAD-QA. Consequently, by interpreting B-rep as structural code, BrepCoder achieves superior generalization across diverse tasks, demonstrating its potential as a general-purpose CAD agent.