A native signed incoherent photonic matrix core on thin-film lithium niobate supporting in situ backpropagation
Abstract
Artificial intelligence workloads increasingly demand computing architectures combining high throughput, energy efficiency, and physical scalability. Here we present a signed incoherent optical matrix multiplier on thin-film lithium niobate that natively supports signed inputs and weights. We demonstrate closed-loop in situ backpropagation on a 16 X 16 photonic core, including forward computation, nonlinear operations, error propagation, and gradient computation. Measured physical outputs directly participate in optimization, thereby incorporating actual device responses and nonidealities into training. The core achieves 8-bit multiplication and 10-bit accumulation precision across 256 channels, maintains 10-bit accuracy in tiled 256 X 256 matrix computation, and further executes Transformer linear operations in a BERT-mini workload. This work presents a fundamental, scalable building block that addresses key limitations in practical optical computing, thereby opening avenues for large-scale, high-efficiency photonic neuromorphic systems.
Related
- Electro-optic comb-driven massive data transmission on monolithically integrated lithium niobate photonic circuits
- All-optical erasing of photorefractive solitonic X-Junctions in lithium niobate thin-film on insulator
- High-speed, compact and low-crosstalk lithium niobate on insulator 2 × 2 optical switch for on-chip integration
- Elastic constants of congruent and nearly stoichiometric lithium niobate crystals by Brillouin light scattering up to 800 °C
- Recent advances in poled lithium niobate
BibTeX
@misc{ren2026native,
title = {{A native signed incoherent photonic matrix core on thin-film lithium niobate supporting in situ backpropagation}},
author = {Yuan Ren and Yong Zheng and Ruixue Liu and Min Wang and Ya Cheng},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.27709},
eprint = {2609.27709},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.27709},
}
RIS
TY - UNPB
TI - A native signed incoherent photonic matrix core on thin-film lithium niobate supporting in situ backpropagation
AU - Yuan Ren
AU - Yong Zheng
AU - Ruixue Liu
AU - Min Wang
AU - Ya Cheng
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.27709
UR - https://arxiv.org/abs/2609.27709
AB - Artificial intelligence workloads increasingly demand computing architectures combining high throughput, energy efficiency, and physical scalability. Here we present a signed incoherent optical matrix multiplier on thin-film lithium niobate that natively supports signed inputs and weights. We demonstrate closed-loop in situ backpropagation on a 16 X 16 photonic core, including forward computation, nonlinear operations, error propagation, and gradient computation. Measured physical outputs directly participate in optimization, thereby incorporating actual device responses and nonidealities into training. The core achieves 8-bit multiplication and 10-bit accumulation precision across 256 channels, maintains 10-bit accuracy in tiled 256 X 256 matrix computation, and further executes Transformer linear operations in a BERT-mini workload. This work presents a fundamental, scalable building block that addresses key limitations in practical optical computing, thereby opening avenues for large-scale, high-efficiency photonic neuromorphic systems.
ER -