CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model
- 1Institute of Data and Information, Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen Guangdong China
- 2Center of Double Helix, Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen Guangdong China
- 3Intelligent Passive Thermal Control Center Research Institute of Tsinghua University in Shenzhen Shenzhen Guangdong China
Abstract
Metamaterials for light manipulation at subwavelength scales face significant design challenges due to their complex and sophisticated structures, leading to the emergence of deep learning as a powerful tool to streamline their design process. However, existing deep learning‐based inverse design methods fall short in the design of reconfigurable metamaterials (RMMs), whose optical characteristics switch between different states upon external stimuli. To address this challenge, CoSP, an intelligent inverse design method for RMMs based on a contrastive pretrained large language model (LLM), is proposed. By performing contrastive pretraining on multi‐state spectra, a well‐trained spectrum encoder is obtained and coupled to a GPT‐style decoder trained end‐to‐end from scratch. Equipped with the preservation of linguistic capabilities, CoSP is capable of describing material structures with target optical properties in natural language. Numerical experiments demonstrate that CoSP can design RMM structures for multi‐state, multi‐band optical responses, showing great potential in versatile applications such as thermal management, optical computation, and telecommunications.
Related
- Inverse design of multi-band terahertz metamaterial sensors with nested topologies via a transformer-conditioned variational autoencoder
- LM2KM: feature extraction from pretrained protein and molecular language models combined with quantum mechanics (QM) features for KM predictions
- Site-Resolved Prediction of Mayr Nucleophilicity with Reactivity-Pretrained Graph Neural Networks
- Tesorai Search: Cloud-based Database Search Engine Boosts Identifications for Mass Spectrometry Proteomics With a Pretrained Peptide-spectrum Deep-learning Model
- Active nanoglass powers metamaterial electrocatalysis.
BibTeX
@article{yang2026cosp,
title = {{CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model}},
author = {Shujie Yang and Yuqi Zhang and Xuzhe Zhao and Yansong Tang and Kaichen Dong},
journal = {Advanced Science},
year = {2026},
month = aug,
doi = {10.1002/advs.76917},
url = {https://doi.org/10.1002/advs.76917},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model
AU - Shujie Yang
AU - Yuqi Zhang
AU - Xuzhe Zhao
AU - Yansong Tang
AU - Kaichen Dong
PY - 2026
DA - 2026/08/11
JO - Advanced Science
DO - 10.1002/advs.76917
UR - https://doi.org/10.1002/advs.76917
AB - Metamaterials for light manipulation at subwavelength scales face significant design challenges due to their complex and sophisticated structures, leading to the emergence of deep learning as a powerful tool to streamline their design process. However, existing deep learning‐based inverse design methods fall short in the design of reconfigurable metamaterials (RMMs), whose optical characteristics switch between different states upon external stimuli. To address this challenge, CoSP, an intelligent inverse design method for RMMs based on a contrastive pretrained large language model (LLM), is proposed. By performing contrastive pretraining on multi‐state spectra, a well‐trained spectrum encoder is obtained and coupled to a GPT‐style decoder trained end‐to‐end from scratch. Equipped with the preservation of linguistic capabilities, CoSP is capable of describing material structures with target optical properties in natural language. Numerical experiments demonstrate that CoSP can design RMM structures for multi‐state, multi‐band optical responses, showing great potential in versatile applications such as thermal management, optical computation, and telecommunications.
SN - 2198-3844
ER -