# Inverse-designed meta processing units for multi-task near-field photonic computing

arXiv: https://arxiv.org/abs/2607.08360 · HTML: https://mlsanity.com/paper/2607.08360/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 40 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 7 of 7)

- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit](https://mlsanity.com/paper/2008.11659/) (2020)
- [Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks](https://mlsanity.com/paper/2205.08501/) (2022)
- [Inverse design of photonic crystals through automatic differentiation](https://mlsanity.com/paper/2003.00379/) (2020)
- [Dual adaptive training of photonic neural networks](https://mlsanity.com/paper/2212.06141/) (2022)

## Abstract (arXiv)

Integrated photonic neural networks require optical operators that are simultaneously compact, matrix-general and compatible with task-level reconfigurability. Here we introduce a meta processing unit (MPU), an inverse-designed near-field photonic device that implements local complex matrix transformations within a shallow-etched silicon region. Each 2x2 operator occupies 9.6 umx4.8 um and is designed as a reusable passive matrix primitive that can be combined with reconfigurable MZI neurons. We demonstrate a 3-bit quantized MZI-equivalent unitary device library with an effective reconstruction precision of 3.32 bits. Beyond unitary operators, we validate arbitrary complex 2x2 matrix fitting and a cascaded 4x4 matrix operation with 92.7% fidelity. We further integrate the MPU with active photonic components and hardware-in-the-loop training, achieving test accuracies of 83.5% and 80.9% on dual-task vowel recognition. In large-scale EMNIST simulations, a fine-grained neuron-level MPU replacement strategy reaches 87.64% average accuracy at 90% shared-MPU replacement, outperforming a layer-level baseline by 7.26 percentage points. These results establish inverse-designed MPUs as compact passive matrix operators for heterogeneous, hardware-adaptive photonic neural networks.