Spatial multiplexing in optical neural networks is repurposed as a trainable representational coordinate, demonstrated in multi-layer architectures for image classification, regression, and hybrid vision-language captioning with over one million optical phase parameters.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
physics.optics 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An all-optical edge-computing platform projects speckle patterns onto a DMD trained in situ by evolutionary optimization to achieve real-time multi-signal separation in fiber sensing with >4 dB enhancement and <-10 dB crosstalk.
citing papers explorer
-
Multi-channel Optical Vision Model
Spatial multiplexing in optical neural networks is repurposed as a trainable representational coordinate, demonstrated in multi-layer architectures for image classification, regression, and hybrid vision-language captioning with over one million optical phase parameters.
-
All-optical Edge Computing for Speckle Sensing Interrogation
An all-optical edge-computing platform projects speckle patterns onto a DMD trained in situ by evolutionary optimization to achieve real-time multi-signal separation in fiber sensing with >4 dB enhancement and <-10 dB crosstalk.