用大模型统一建模多种超表面，提升设计效率与泛化能力
Towards a universal meta-optics solver via large language models
- 将不同超表面结构转为统一文本指令格式，用大模型联合建模
- 跨8类超表面平均降低均方误差56.5%，性能优于单一类别模型
- 适合需要快速适配多类型超表面设计的研究者与工程师
超表面设计亟需能跨异构器件家族快速运行的通用模型，而非为每类几何结构单独训练代理模型。传统神经网络代理依赖固定维度描述符、特定家族输出格式及重复架构调优，限制了其在多样元原子间的可扩展性。本文提出一种统一的大语言模型（LLM）流程，用于多家族超表面建模与逆向设计。将几何结构、设计参数与光学响应通道转化为共享的指令跟随文本格式，并基于此对Gemma-2-9B进行微调，覆盖8类超表面家族。相比单家族基线模型，该联合模型同时预测所有家族光学响应，且每类平均降低均方误差56.5%。相同表示也用于逆向设计。结果表明，共享序列化LLM接口可为跨家族超表面设计提供可行路径，显著减少对任务特异性代理架构的需求。
原文摘要 · Abstract (English)
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.
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。