Physics-informed generative AI for semiconductor manufacturing: Enforcing hard physical constraints in generative models by construction

面向半导体制造的物理信息生成式 AI：在生成模型中构建硬物理约束

Abstract: Generative models are increasingly used to propose designs, data, and control actions for physical systems, yet many such systems are governed by hard physical constraints rather than by perceptual plausibility. Semiconductor manufacturing provides a demanding test case: generated masks, layouts, synthetic defect data, and process recipes must obey lithography, transport, reaction, and device-physics constraints, because physically invalid samples are not merely low quality but unusable.

摘要： 生成式模型正越来越多地被用于为物理系统提出设计、数据和控制方案，然而许多此类系统受限于硬性物理约束，而非仅仅取决于感知上的合理性。半导体制造提供了一个极具挑战性的测试案例：生成的掩模、版图、合成缺陷数据和工艺配方必须严格遵守光刻、传输、反应和器件物理约束，因为物理上无效的样本不仅质量低劣，而且根本无法使用。

This Perspective argues that semiconductor manufacturing exposes a broader computational-science challenge, namely that generative AI for constrained physical domains must be physics-informed by construction, not corrected only through post-hoc filtering. We survey the emerging architectural toolkit, including physics-informed diffusion, PDE-constrained variational models, neural-operator priors, and conservation-law-respecting generative networks, and show how it connects to differentiable lithography, TCAD, process simulation, and autonomous experimentation.

本观点文章认为，半导体制造揭示了一个更广泛的计算科学挑战，即针对受限物理领域的生成式 AI 必须在构建时就融入物理信息，而非仅仅通过事后过滤进行修正。我们调研了新兴的架构工具包，包括物理信息扩散模型、偏微分方程（PDE）约束变分模型、神经算子先验以及遵循守恒定律的生成网络，并展示了它们如何与可微光刻、TCAD（技术计算机辅助设计）、工艺仿真和自主实验相结合。

We identify four integration patterns between generative models and physics-based simulators, and we propose a research agenda centered on physics-fidelity benchmarks, differentiable simulator infrastructure, and multimodal foundation models for physical design and manufacturing. The central claim is analytical rather than rhetorical: where physical validity is the binding criterion of success, architectures that enforce it by construction should be expected to outperform those that filter for it after the fact, and the fab is the setting where this distinction is sharpest.

我们确定了生成模型与基于物理的仿真器之间的四种集成模式，并提出了一个以物理保真度基准、可微仿真器基础设施以及用于物理设计和制造的多模态基础模型为核心的研究议程。其核心主张是分析性的而非修辞性的：在物理有效性作为成功的决定性标准时，通过构建强制执行该约束的架构，预期将优于那些事后进行过滤的架构，而晶圆厂正是这一区别体现得最为显著的场景。