用编译器做裁判，高效评估文本生成的CAD模型质量
CAD-Judge: Toward Efficient Morphological Grading and Verification for Text-to-CAD Generation
- 用编译器直接输出奖励信号，替代昂贵的视觉模型评分
- 在多个数据集上达到顶尖性能，且推理速度显著提升
- 适合需要快速验证和优化工业设计生成的开发者
计算机辅助设计（CAD）模型广泛应用于工业设计、仿真与制造流程。文本到CAD系统旨在从文本描述生成可编辑、通用的CAD模型，大幅降低传统CAD工作流的复杂性与入门门槛。然而，渲染CAD模型耗时长，使用视觉语言模型（VLM）进行评审成本高，且可能引发奖励欺骗问题，影响系统可靠性。为此，我们提出CAD-Judge，一种新型可验证的奖励机制，用于高效、准确地进行CAD偏好评分与语法校验。采用编译器作为裁判模块（CJM），提供快速、直接的奖励信号，通过前景理论最大化生成实用性以对齐模型。为进一步提升测试阶段的鲁棒性，引入简单高效的代理式CAD生成方法，并采用编译器作为评审模块（CRM），能高效验证生成的CAD模型并实现自我修正。在多个具有挑战性的CAD数据集上的实验表明，本方法在保持卓越效率的同时达到当前最优性能。
原文摘要 · Abstract (English)
Computer-Aided Design (CAD) models are widely used across industrial design, simulation, and manufacturing processes. Text-to-CAD systems aim to generate editable, general-purpose CAD models from textual descriptions, significantly reducing the complexity and entry barrier associated with traditional CAD workflows. However, rendering CAD models can be slow, and deploying VLMs to review CAD models can be expensive and may introduce reward hacking that degrades the systems. To address these challenges, we propose CAD-Judge, a novel, verifiable reward system for efficient and effective CAD preference grading and grammatical validation. We adopt the Compiler-as-a-Judge Module (CJM) as a fast, direct reward signal, optimizing model alignment by maximizing generative utility through prospect theory. To further improve the robustness of Text-to-CAD in the testing phase, we introduce a simple yet effective agentic CAD generation approach and adopt the Compiler-as-a-Review Module (CRM), which efficiently verifies the generated CAD models, enabling the system to refine them accordingly. Extensive experiments on challenging CAD datasets demonstrate that our method achieves state-of-the-art performance while maintaining superior efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。