发表机构
Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology; AI Research Team, Narnia Labs（韩国科学技术院赵春植移动研究生院; 纳尼亚实验室AI研究团队）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本工作将冻结的文本到图像扩散模型作为免训练生成先验，通过分数蒸馏采样融入密度拓扑优化，实现零样本肋条设计，在245次运行中显著降低柔度，并生成可用于CAD的几何体。
AI 中文摘要
自然承重模式如叶脉、骨小梁和蜘蛛网实现了单位质量的高刚度，然而经典拓扑优化器很少能达到此类几何形状，且很少有优化器允许工程师通过自然语言表达结构设计意图。本工作将冻结的文本到图像扩散模型视为免训练的设计知识来源，并通过分数蒸馏采样将其提炼到基于密度的拓扑优化的物理循环中，使得文本提示成为工程师意图的显式、机器可解释的表示。每次迭代中，提示诱导的生成梯度与有限元灵敏度相结合，让物理决定哪些提示诱导的特征得以保留。在跨越四个几何域和两种物理机制的245次主要SDS运行中，49个提示-域组合中有38个实现了统计显著的柔度降低（机械最高降低$-31.5\%$，热弹性最高降低$-23.0\%$），优于基于梯度的基线。跨域形态分析识别出改进的重复结构特征：在大多数域中，生成先验抑制了肋条骨架中的末端分支，端点-柔度相关性$r = +0.56$至$+0.99$。具有$\eta$延续的Heaviside投影解决了这种扩散-物理耦合中显著的中间密度倾向（从$42.6\%$降至$<3\%$），自动化的基于骨架的流程将优化后的密度场转换为可用于计算机辅助设计的候选几何体。通过改变文本提示跨域、载荷条件和物理目标重新定向生成先验，每个新问题的物理设置单独指定，该框架利用预训练生成模型作为工程设计的可重用、免训练先验。
英文摘要
Natural load-bearing patterns such as leaf venation, trabecular bone, and spider webs achieve high stiffness per unit mass, yet classical topology optimizers rarely reach such geometries, and few let engineers express structural design intent through natural language. This work treats a frozen text-to-image diffusion model as a training-free source of design knowledge and distills it into the physics loop of density-based topology optimization via score distillation sampling, so that a text prompt becomes an explicit, machine-interpretable representation of engineer intent. The prompt-induced generative gradient and the finite element sensitivity are combined at every iteration, letting physics decide which prompt-induced features survive. In 245 primary SDS runs spanning four geometric domains and two physics regimes, 38 of 49 prompt--domain combinations achieved statistically significant compliance reductions (up to $-31.5\%$ mechanical and $-23.0\%$ thermoelastic), outperforming gradient-based baselines. Cross-domain morphological analysis identifies a recurring structural signature of improvement: in most domains the generative prior suppresses dead-end branches in the rib skeleton, with endpoint--compliance correlation $r = +0.56$ to $+0.99$. A Heaviside projection with $β$-continuation resolves a pronounced intermediate-density tendency in this diffusion--physics coupling ($42.6\%$ to $<3\%$), and an automated skeleton-based pipeline converts optimized density fields into \rev{candidate geometry ready for computer-aided design. By retargeting the generative prior across domains, loading conditions, and physics objectives through a change of text prompt, with each new problem's physics setup specified separately, the framework uses a pretrained generative model as a reusable, training-free prior for engineering design.
