MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design

TL;DR

MOCLIP is a large-scale nanophotonic foundation model that uses contrastive learning to enable rapid inverse design, high-density optical storage, and scalable photonic applications, overcoming data limitations in the field.

Contribution

This work introduces MOCLIP, a novel nanophotonic foundation model that integrates geometry and spectra in a shared space using contrastive learning, enabling fast inverse design and high-density optical storage.

Findings

Achieves 0.2 million samples/sec inverse design prediction.

Designs a 4-inch wafer with high-density metasurfaces in minutes.

Reaches 97% accuracy in latent-space optimization.

Abstract

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.