As a promising model in Quantum Machine Learning (QML), Quantum Generative Adversarial Networks (QGANs) are rapidly advancing, offering applications in image processing and generation. However, another emerging paradigm represents an image as a Quantum Implicit Neural Representation (QINR). In this work, we propose a novel architectural technique for building QINR-based QGAN to enhance the quality of images generated by QGANs. Additionally, we integrate classical techniques, such as Gradient Penalty and Wasserstein distance, to train QINR-QGAN. In image generation tasks, we demonstrated that QINR-QGAN can achieve performance comparable to state-of-the-art (SOTA) models while significantly reducing the number of trainable quantum parameters. Specifically, QINR-QGAN reduced the trainable quantum parameters by nearly 10 times compared to PQWGAN (Tsang et al. in IEEE Trans. Quantum Eng. 4:1–19, 2023) and Quantum AnoGAN (Herr et al. Quantum Sci. Technol. 6(4): 045004, 2021), demonstrating its superior efficiency in parameter optimization without sacrificing performance. Furthermore, we conducted experiments on the CelebA dataset to tackle a more complex task and generate larger images ( $78\times 64$ ). The results indicate that our model is capable of successfully completing the face generation task.

Variational quantum algorithms (VQAs) have been successfully applied to quantum approximate optimization algorithms, variational quantum compiling, and quantum machine learning models. The performance of VQAs is significantly influenced by the architecture of parameterized quantum circuits (PQCs). Quantum architecture search aims to automatically discover high-performance quantum circuits for specific VQA tasks. Quantum architecture search algorithms that utilize both SuperCircuit training and a parameter-sharing approach can save computational resources. If we directly follow the parameter-sharing approach, the SuperCircuit has to be trained to compensate for the worse search space. To address the challenges posed by the worse search space, we introduce an optimization strategy known as the efficient continuous evolutionary approach using Non-dominated Sorting Genetic Algorithm-II (NSGA-II). Then, we leverage prior information (symmetric property) designing Structure Symmetric Pruning for removing redundant gates of the searched ansatz. Experiments show that the efficient continuous evolutionary approach can search for more quantum architectures with better performance; the number of high-performance ansatzes obtained by our method is 10% higher than that in the literature (Du et al. in npj Quantum Inf. 8:62, 2022). The application of Structure Symmetric Pruning effectively reduces the number of parameters in quantum circuits without compromising their performance significantly. In binary classification tasks, the pruned quantum circuits exhibit an average accuracy reduction of 0.044 compared to their unpruned counterparts.

As quantum computing continues to advance alongside machine learning, Quantum Generative Adversarial Networks (QGANs) have gained attention as a compelling generative modeling approach in quantum machine learning. Despite their potential, most existing QGAN implementations rely on manually designed quantum circuits, which often suffer from high complexity and limited scalability. To overcome these limitations, we propose a Quantum Architecture Search (QAS) method built upon the SuperCircuit framework. This approach enables the automatic discovery of efficient quantum circuit structures tailored for generative tasks, thereby reducing gate count. However, applying SuperCircuit-based QAS directly to QGANs presents two primary challenges: an expansive search space and a lack of guarantees regarding circuit efficiency. To mitigate these issues, we incorporate Principal Component Analysis (PCA) and a PCA-guided feature distribution mechanism during preprocessing. This strategy both compresses the search space and ensures balanced allocation of principal components across sub-generators. Extensive experiments confirm the viability of the proposed framework. When employing the discovered quantum circuits, QAS-QGAN achieves image quality comparable to a state-of-the-art (SOTA) baseline (Silver et al 2023 2023 IEEE/CVF Int. Conf. on Computer Vision (ICCV) pp 7007–16) on both the MNIST and Fashion MNIST datasets. Notably, our model reduces the number of two-qubit gates by 52.08% on MNIST and 52.92% on Fashion MNIST, highlighting substantial improvements in quantum resource efficiency. Furthermore, the model successfully generates high-resolution facial images ( 109 × 89 ) on the CelebA dataset, demonstrating strong scalability and practical applicability.

While classical steganography achieves maturity in digital media, hiding arbitrary quantum states (α|0 + β|1) has emerged as an intriguing frontier. To address this problem, we establish a formal model of controllable random perturbation unitaries for single/multi-stego state tasks. We progressively explore Quantum Autoencoder (QAE) structures through three stages: starting from single-state scenarios without perturbation, advancing to perturbed conditions, and finally extending to multi-state tasks. We design two perturbation-based encoding schemes using Quantum Autoencoders (QAE): the simple scheme (QAE-DD) leverages the inverse application of encoding-decoding modules, while the improved scheme (QAE-OSP) incorporates orthogonal projection routing and parallel subnetworks to restructure the hidden-layer architecture. In 3-qubit entangled-state simulations with data scales n ≤ 10 and perturbation strengths ε ∈ [0, 1], QAE-DD performs well under low perturbation, whereas QAE-OSP maintains higher fidelity between the carrier and secret states under high perturbation conditions (e.g., n = 5, ε = 0.6), with fidelity values F ρ stego , ρstego = 0.91 / F (ρ S , ρS) = 0.84 providing a reference for network design. Finally, we extend the single-carrier ("1 + 1") task to the multi-carrier ("1 + N ") scenario by constructing a "centroid" state training set based on the principal component of carrier-state groups and validating the applicability of both models. Under the conditions n = 5 and ε = 0.6, the QAE-OSP model successfully improves the average fidelity between multiple secret states and carrier states from 0.68 to 0.90, demonstrating its capability to aggregate multiple carriers to enhance overall concealment. Although the present study covers only small-scale data and networks, it lays the groundwork for a neural network framework that covertly embeds arbitrary quantum states into high-dimensional quantum states, providing a basis for future exploration.