BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning

TL;DR

BrepCoder is a unified multimodal large language model designed for multi-task reasoning on Boundary Representation (B-rep) CAD data, converting CAD sequences into code to perform diverse tasks with improved generalization.

Contribution

It introduces a novel approach to CAD modeling by interpreting B-rep as code and employs a two-stage training strategy for multi-task learning, addressing limitations of task-specific models.

Findings

Achieves superior performance across multiple CAD tasks.

Effectively generalizes to diverse downstream applications.

Demonstrates potential as a general-purpose CAD agent.

Abstract

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.