ICCK

Dr Xinye Xu

Shangrao Normal University, Shangrao 334001, Jiangxi, China, CN

Section 01

Academic Profile

No academic profile information available at the moment.

Section 02

ICCK Publications

Export all 1 BibTeX RIS
Open Access | Research Article | 20 November 2026
PADS: Physics-Aware, Model-Free Diffusion Training for Robust Generative Intelligence in Optical Neural Networks
Optical Wireless Communication | Volume 1, Issue 1: 60-75, 2026 | DOI: 10.62762/OWC.2026.824441
Abstract
Integrating diffusion models into physical computing systems such as optical neural networks (ONNs) enables low-power, high-speed generative intelligence but faces two critical barriers: the simulation-to-reality (sim2real) gap and the prohibitive computational cost of gradient-based training with differentiable simulators. The iterative denoising of diffusion models (typically 1000 steps) accumulates errors from physical imperfections (aberrations, misalignments, quantization), causing severe performance degradation when the models are deployed on real hardware. To address this, we propose PADS (Physics-Aware Diffusion Training via Score Gradient Estimation), a model-free optimization frame... More >

Graphical Abstract
PADS: Physics-Aware, Model-Free Diffusion Training for Robust Generative Intelligence in Optical Neural Networks