Toward a Universal Meta-Optics Solver via Large Language Models.
- 1The Pennsylvania State University , Department of Electrical Engineering, University Park, Pennsylvania16802, United States.
- 2School of Electronics and Information Technology, Sun Yat-Sen University, Guangzhou510275, China.
Abstract
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 limit their scalability across heterogeneous meta-atoms. Here, we present a unified large language model (LLM) workflow for multifamily 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 the 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.
Versions
Related
- Large Language Models in Chemistry: Opportunities, Limitations, and Hallucination Risks
- How Chemical Evidence Shapes Mechanistic Reasoning and Prediction by Large Language Models: Fine-Grained Inference in Nucleoside-Derived Supramolecular Gelation
- Dataset-level reliability and quality control for metallurgical data structured with large language models
- Lost in Chemical Space: Local Open-Source Large Language Models Display Model-Dependent Adherence to Reference Data in Molecular Generation
- BigMixSolDB: Extraction of a solubility database in solvent mixtures with an uncertainty-quantified large language model-based pipeline
BibTeX
@article{zhang2026toward,
title = {{Toward a Universal Meta-Optics Solver via Large Language Models.}},
author = {Huanshu Zhang and Lei Kang and Yuyan Chen and Luxiang Wang and Zhaolong Cao and Douglas H Werner},
journal = {Nano letters},
year = {2026},
month = sep,
doi = {10.1021/acs.nanolett.6c03323},
url = {https://europepmc.org/article/MED/42915372},
note = {CC BY},
}
RIS
TY - JOUR
TI - Toward a Universal Meta-Optics Solver via Large Language Models.
AU - Huanshu Zhang
AU - Lei Kang
AU - Yuyan Chen
AU - Luxiang Wang
AU - Zhaolong Cao
AU - Douglas H Werner
PY - 2026
DA - 2026/09/01
JO - Nano letters
DO - 10.1021/acs.nanolett.6c03323
UR - https://europepmc.org/article/MED/42915372
AB - 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 limit their scalability across heterogeneous meta-atoms. Here, we present a unified large language model (LLM) workflow for multifamily 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 the 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.
SN - 1530-6984
SN - 1530-6992
ER -