MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design
This provides a scalable platform for nanophotonic inverse design, enabling rapid design of high-density metasurfaces and optical storage with a density six times higher than commercial media, though it is incremental in applying foundation models to a new domain.
The paper tackles the lack of large datasets for foundation models in nanophotonics by introducing MOCLIP, which integrates metasurface geometry and spectra using contrastive learning, achieving high-throughput zero-shot prediction at 0.2 million samples per second and generative optimization with 97% accuracy.
Foundation models (FM) are transforming artificial intelligence by enabling generalizable, data-efficient solutions across different domains for a broad range of applications. However, the lack of large and diverse datasets limits the development of FM in nanophotonics. This work presents MOCLIP (Metasurface Optics Contrastive Learning Pretrained), a nanophotonic foundation model that integrates metasurface geometry and spectra within a shared latent space. MOCLIP employs contrastive learning to align geometry and spectral representations using an experimentally acquired dataset with a sample density comparable to ImageNet-1K. The study demonstrates MOCLIP inverse design capabilities for high-throughput zero-shot prediction at a rate of 0.2 million samples per second, enabling the design of a full 4-inch wafer populated with high-density metasurfaces in minutes. It also shows generative latent-space optimization reaching 97 percent accuracy. Finally, we introduce an optical information storage concept that uses MOCLIP to achieve a density of 0.1 Gbit per square millimeter at the resolution limit, exceeding commercial optical media by a factor of six. These results position MOCLIP as a scalable and versatile platform for next-generation photonic design and data-driven applications.