发表机构
JoyIndustrial（卓异工业）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
VisCAD是一款多模态工业CAD智能基础模型套件，其核心VisCAD-M1在零件级设计生成任务上优于现有模型，作为测试时验证器可进一步提升性能，配套领域特定工具链在复杂装配生成上也表现出色。
AI 中文摘要
工业产品的AI辅助计算机辅助设计（CAD）涉及两个具有挑战性的阶段：零件级生成需将渲染图、文本描述、二维图纸、真实照片等多种形式的用户意图映射为CAD领域特定语言中的可执行程序；装配级生成则还需处理零件间的交互、规划配合关系、估计位姿并正确放置所有零件。现有专用CAD模型通常在渲染图或文本等狭窄输入域上训练，泛化能力较差；而通用前沿模型虽覆盖更广泛输入，但在CAD各领域表现不一致。本文提出VisCAD，一款旨在为真实工业产品提供广泛泛化能力与强大CAD能力的基础模型套件。其核心是VisCAD-M1，一款27B参数的模型，通过中间训练和后训练进行零件级设计生成。在PubCADBench和RealCADBench上，VisCAD-M1在所有评估模型中达到最高零件级平均分数，为0.5540，而最强前沿模型为0.5496。将VisCAD-M1作为测试时验证器可进一步将分数提升至0.5797，较之前的最优水平实现约5%的相对提升。VisCAD还包含一个领域特定工具链，该工具链利用前沿模型进行复杂装配生成，在定量和定性评估中均表现出优于通用工具链的优势。
英文摘要
AI-assisted computer-aided design (CAD) for industrial products involves two challenging phases. Part-level generation maps diverse forms of user intent, including renders, text descriptions, 2D drawings, and real photographs, to executable programs in a CAD domain-specific language. Assembly-level generation must additionally handle interacting parts, plan mating relations, estimate poses, and place all parts correctly. Existing specialized CAD models are commonly trained on narrow input domains, such as renders or texts, and often generalize poorly, while general-purpose frontier models cover broader inputs but perform inconsistently across CAD domains. We present VisCAD, a foundation model suite designed to provide both broad generalization and strong CAD capability for realistic industrial products. At its core is VisCAD-M1, a 27B model trained through mid-training and post-training for part-level design generation. On PubCADBench and RealCADBench, VisCAD-M1 achieves the highest average part-level score among the evaluated models, reaching 0.5540 compared with 0.5496 for the strongest frontier model. Reusing VisCAD-M1 as a test-time verifier can further raise the score to 0.5797, an approximately 5 percent relative improvement over the previous state of the art. VisCAD also includes a domain-specific harness that leverages frontier models for complex assembly generation and demonstrates advantages over general-purpose harnesses in both quantitative and qualitative evaluations.
CommentsTechnical report
