Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing
Abstract
All-optical diffractive neural networks (DNNs) offer low latency, low energy consumption, and massive parallelism. However, their scalability in terms of network scale and multi-task processing remains limited. Here, we experimentally demonstrate a large-scale metasurface-based diffractive learning machine for angle-multiplexed multi-task processing. Our system employs a metasurface-based reflection cavity to realize a five-layer DNN comprising 115 million fixed, untrained diffractive nodes within a compact volume of 216 mm^3. By integrating this large-scale, untrained DNN with a lightweight, trainable digital backend containing only 7,680 parameters, our system experimentally achieves an accuracy of 95.3% on the standard full-scale CIFAR-10 dataset, significantly outperforming previous optical neural networks and rivaling large-scale digital models. Using a novel incident-angle-multiplexing scheme, our system experimentally achieves parallel processing of 11 tasks with negligible performance degradation, representing the largest multi-task processing capacity reported to date. Our work provides a scalable and energy-efficient solution for high-performance edge computing.
Related
- Learned Diffractive Optics for Quantum-Optimal Inference
- Real-time adaptive optics compensation for turbulence-impaired OAM-multiplexed optical communications
- Edge-enhanced diffractive neural networks based on spin-multiplexed nonlocal metasurfaces
- Wavelength-Multiplexed Nonlinear Computing with a Single-Layer Diffractive Optical Processor
- Wavelength-Multiplexed 2D Beam Steering via a Passive Diffractive Network
BibTeX
@misc{luo2026metaopticsbased,
title = {{Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing}},
author = {Mingcheng Luo and Jianmin Xiong and Jiayong Peng and Jingtian Hu and Hongwei Chen and Chester Shu and Chaoran Huang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.25792},
eprint = {2609.25792},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.25792},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing
AU - Mingcheng Luo
AU - Jianmin Xiong
AU - Jiayong Peng
AU - Jingtian Hu
AU - Hongwei Chen
AU - Chester Shu
AU - Chaoran Huang
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.25792
UR - https://arxiv.org/abs/2609.25792
AB - All-optical diffractive neural networks (DNNs) offer low latency, low energy consumption, and massive parallelism. However, their scalability in terms of network scale and multi-task processing remains limited. Here, we experimentally demonstrate a large-scale metasurface-based diffractive learning machine for angle-multiplexed multi-task processing. Our system employs a metasurface-based reflection cavity to realize a five-layer DNN comprising 115 million fixed, untrained diffractive nodes within a compact volume of 216 mm^3. By integrating this large-scale, untrained DNN with a lightweight, trainable digital backend containing only 7,680 parameters, our system experimentally achieves an accuracy of 95.3% on the standard full-scale CIFAR-10 dataset, significantly outperforming previous optical neural networks and rivaling large-scale digital models. Using a novel incident-angle-multiplexing scheme, our system experimentally achieves parallel processing of 11 tasks with negligible performance degradation, representing the largest multi-task processing capacity reported to date. Our work provides a scalable and energy-efficient solution for high-performance edge computing.
ER -