发表机构
The Pennsylvania State University; School of Electronics and Information Technology, Sun Yat-Sen University（宾夕法尼亚州立大学; 中山大学电子与信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于Gemma-2-9B大语言模型的统一工作流，将多家族超表面相关信息转换为文本格式微调，实现跨家族光学响应预测与逆设计，MSE平均降低56.5%，减少了对任务特定架构的需求。
AI 中文摘要
超表面设计日益需要能够跨结构不同器件家族运行的快速模型，而非为每种几何类别单独训练代理模型。传统神经网络代理常依赖固定维度描述符、家族特定输出格式及重复架构调整，限制了其在异构超原子间的可扩展性。本文提出一种统一的大语言模型（LLM）工作流，用于多家族超表面建模与逆设计：将几何、设计参数及光学响应通道转换为统一的指令遵循文本格式，在8个超表面家族上微调Gemma-2-9B。与单家族基线相比，该联合模型可同时预测所有超表面家族的光学响应，且每个家族的均方误差（MSE）平均降低56.5%；相同表示也用于逆设计。这些结果表明，共享的基于序列的LLM接口为跨家族超表面设计提供了可行路径，同时减少了对任务特定代理架构的需求。
英文摘要
Metasurface design increasingly requires fast models that can operate across structurally distinct device families, rather than retraining a separate surrogate for every geometry class. Conventional neural network surrogates often depend on fixed-dimensional descriptors, family-specific output formats, and repeated architecture tuning, which limits their scalability across heterogeneous meta-atoms. Here, we present a unified large language model (LLM) workflow for multi-family metasurface modeling and inverse-design. Geometries, design parameters, and optical response channels were converted into a shared instruction-following text format and used to fine-tune Gemma-2-9B across 8 metasurface families. Compared with single-family baselines, the joint model simultaneously predicted the optical responses of all metasurface families while reducing the MSE for each family by an average of 56.5%. The same representation was also used for inverse design. These results show that a shared sequence-based LLM interface can provide a practical route to cross-family metasurface design while reducing the need for task-specific surrogate architectures.
CommentsAccepted for publication in Nano Letters
DOI：10.1021/acs.nanolett.6c03323
