Photonic Mixture-of-Experts for scalable multi-task on-chip optical neural networks
Wencan Liu, Zhenghang Zhang, Peng Meng Chan, Run Sun, Yutong He, Yuhao Wang, Caihua Zhang, Sigang Yang, Tingzhao Fu, Yuyao Huang, Chaoran Huang, Hongwei Chen · 2026
Read Photonic Mixture-of-Experts for scalable multi-task on-chip optical neural networks by Wencan Liu, Zhenghang Zhang, Peng Meng Chan, Run Sun, Yutong He, Yuhao Wang, Caihua Zhang, Sigang Yang, Tingzhao Fu, Yuyao Huang, Chaoran Huang, Hongwei Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13396494.txt.
Description
Wencan Liu and colleagues present a photonic mixture-of-experts chip for scalable multi-task optical neural networks in a 2026 study. Photonic computing promises energy-efficient, high-bandwidth AI, but depth-dependent designs, optical losses, and reconfiguration costs have limited scale.
Expanding network width rather than depth, the team built parallel photonic cores as expert networks, routing inputs dynamically without changing physical optical weights. A fabricated chip with three diffraction-based experts and 18 parallel kernels in a tiny 0.067 square millimeter core handled multi-domain image classification. The paper offers a scalable optical AI architecture.
Catalog record
| CREATOR | Wencan Liu, Zhenghang Zhang, Peng Meng Chan, Run Sun, Yutong He, Yuhao Wang, Caihua Zhang, Sigang Yang, Tingzhao Fu, Yuyao Huang, Chaoran Huang, Hongwei Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |