Abstract:Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) this http URL, 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.
From: Hyungki Kim [view email]
[v1]
Wed, 25 Feb 2026 12:44:28 UTC (582 KB)
[v2]
Mon, 2 Mar 2026 04:18:48 UTC (581 KB)
[v3]
Thu, 25 Jun 2026 03:36:56 UTC (1,312 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。