This paper introduces the Kaiwu-PyTorch-Plugin (KPP) to bridge Deep Learning and Photonic Quantum Computing across multiple dimensions. KPP integrates the Coherent Ising Machine into the PyTorch ecosystem, addressing classical inefficiencies in Energy-Based Models. The framework facilitates quantum integration in three key aspects: accelerating Boltzmann sampling, optimizing training data via Active Sampling, and constructing hybrid architectures like QBM-VAE and Q-Diffusion. Empirical results on single-cell and OpenWebText datasets demonstrate KPPs ability to achieve SOTA performance, validating a comprehensive quantum-classical paradigm.
Cite
@article{arxiv.2602.19114,
title = {Kaiwu-PyTorch-Plugin: Bridging Deep Learning and Photonic Quantum Computing for Energy-Based Models and Active Sample Selection},
author = {Hongdong Zhu and Qi Gao and Yin Ma and Shaobo Chen and Haixu Liu and Fengao Wang and Tinglan Wang and Chang Wu and Kai Wen},
journal= {arXiv preprint arXiv:2602.19114},
year = {2026}
}