MOCLIP: a foundation model for large-scale nanophotonic inverse design
- 1PRIMALIGHT, Faculty of Electrical Engineering; Applied Mathematics and Computational Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
- 2PRIMALIGHT, Faculty of Electrical Engineering; Applied Mathematics and Computational Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia. [email protected]
Abstract
Foundation models are transforming artificial intelligence by enabling generalizable, data-efficient solutions across diverse domains and applications. However, the lack of large and diverse datasets remains a key barrier to their development in nanophotonics. This work presents MOCLIP (Metasurface Optics Contrastive Learning Pretrained), a nanophotonic foundation model that encodes metasurfaces’ structural and spectral information into a shared latent space via contrastive learning, using an experimentally acquired dataset with sample density approaching the scale of ImageNet-1K. The study demonstrates MOCLIP’s inverse design capabilities, including high-throughput zero-shot prediction at 2 ⋅ 105 samples per second, full-wafer design of an entire 4-inch substrate in minutes, and latent space optimization reaching 95% accuracy. This work further introduces an optical information storage concept that leverages MOCLIP to achieve a storage density of 0.1 Gbit/mm2 at the resolution limit, surpassing commercial optical media by a factor of six. Together, these results position MOCLIP as a scalable, versatile platform for next-generation photonic design and data-driven applications. The foundation model MOCLIP brings large-scale AI to nanophotonics. Trained on experimental wafer scale data, it designs metasurfaces at 200,000 samples per second with over 95% accuracy, enabling optical memory six times denser than commercial ones.
Related
- CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model
- ChemEidos: Synthesis-Aware Multimodal Foundation Models for Domain-Specific Generative Design
- Interpretable inverse design of optical multilayer thin films based on global neural adjoint
- Machine learning-driven inverse design of high-hardness multi-principal element alloys through symbolic regression
- Machine learning–driven inverse design of nanofiltration membranes for selective Mg2+/Na+ separation
BibTeX
@article{rodionov2026moclip,
title = {{MOCLIP: a foundation model for large-scale nanophotonic inverse design}},
author = {Sergei Rodionov and Arturo Burguete Lopez and Maksim O. Makarenko and Qizhou Wang and Fedor Getman and Andrea Fratalocchi},
journal = {Nature Communications},
year = {2026},
month = aug,
doi = {10.1038/s41467-026-76714-x},
url = {https://doi.org/10.1038/s41467-026-76714-x},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - MOCLIP: a foundation model for large-scale nanophotonic inverse design
AU - Sergei Rodionov
AU - Arturo Burguete Lopez
AU - Maksim O. Makarenko
AU - Qizhou Wang
AU - Fedor Getman
AU - Andrea Fratalocchi
PY - 2026
DA - 2026/08/19
JO - Nature Communications
DO - 10.1038/s41467-026-76714-x
UR - https://doi.org/10.1038/s41467-026-76714-x
AB - Foundation models are transforming artificial intelligence by enabling generalizable, data-efficient solutions across diverse domains and applications. However, the lack of large and diverse datasets remains a key barrier to their development in nanophotonics. This work presents MOCLIP (Metasurface Optics Contrastive Learning Pretrained), a nanophotonic foundation model that encodes metasurfaces’ structural and spectral information into a shared latent space via contrastive learning, using an experimentally acquired dataset with sample density approaching the scale of ImageNet-1K. The study demonstrates MOCLIP’s inverse design capabilities, including high-throughput zero-shot prediction at 2 ⋅ 105 samples per second, full-wafer design of an entire 4-inch substrate in minutes, and latent space optimization reaching 95% accuracy. This work further introduces an optical information storage concept that leverages MOCLIP to achieve a storage density of 0.1 Gbit/mm2 at the resolution limit, surpassing commercial optical media by a factor of six. Together, these results position MOCLIP as a scalable, versatile platform for next-generation photonic design and data-driven applications. The foundation model MOCLIP brings large-scale AI to nanophotonics. Trained on experimental wafer scale data, it designs metasurfaces at 200,000 samples per second with over 95% accuracy, enabling optical memory six times denser than commercial ones.
SN - 2041-1723
ER -