SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training
By Pingchuan Ma, Ziang Yin, Qi Jing, Zhengqi Gao, Nicholas Gangi, Boyang Zhang, Tsung-Wei Huang, Zhaoran Huang, Duane S. Boning, Yu Yao and Jiaqi Gu†
This repo is the official implementation of "SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training".
@inproceedings{pma2026sp2rint,
title={{SP$^2$RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training}},
author={Pingchuan Ma and Ziang Yin and Qi Jing and Zhengqi Gao and Nicholas Gangi and Boyang Zhang and Tsung-Wei Huang and Zhaoran Huang and Duane S. Boning and Yu Yao and Jiaqi Gu},
year={2026},
booktitle={Design Automation Conference (DAC)},
url={https://arxiv.org/abs/2505.18377},
}
Pingchuan Ma, Ziang Yin, Qi Jing, Zhengqi Gao, Nicholas Gangi, Boyang Zhang, Tsung-Wei Huang, Zhaoran Huang, Duane S. Boning, Yu Yao and Jiaqi Gu, "SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training," Design Automation Conference (DAC), July 2026.