Photonic Mixture-of-Experts for scalable multi-task on-chip optical neural networks

Photonic computing offers an energy-efficient, high-bandwidth platform for artificial intelligence (AI) but currently faces scalability bottlenecks stemming from depth-dependent designs, linear optical structures, and intrinsic optical losses, along with high hardware and reconfiguration costs for multi-task processing. Here, we present a scaling paradigm that circumvents these limitations by expanding network width rather than depth, leveraging the intrinsic parallelism of photonics. We implement a scalable Photonic Mixture-of-Experts (PMoE) architecture, where parallel photonic cores function as expert networks. By dynamically routing inputs to these experts, the PMoE efficiently executes multi-task workloads without altering the physical optical weights. We fabricated a PMoE chip integrating three collaborative diffraction-based expert networks, featuring 18 parallel kernels within a compact intrinsic computational-core footprint of 0.067 mm2. Experimentally, the PMoE chip achieves multi-domain image classification with an average accuracy of 97.1%. While offering further scalability, this approach outperforms conventional optical networks and reduces digital parameter overhead by 67%. Our work underscores the scalability and efficiency of the PMoE architecture for next-generation large-scale photonic AI processors. Optical computing could accelerate AI, but struggles to scale optical neural networks for diverse tasks. Here, the authors demonstrate a scalable photonic mixture-of-experts chip that expands network capacity in width using parallel optical experts for multi-task processing.