The emergence of deep vision models such as convolutional neural networks and vision transformers has revolutionized computer vision, enabling significant advancements in image classification, object detection, and segmentation. In parallel, the rapid development of quantum computing has spurred interest in quantum machine learning (QML), which integrates the strengths of quantum computation with the representational power of deep learning. In QML, parameterized quantum circuits offer the potential to capture complex image features, define complex decision boundaries, and provide other computational advantages. This paper investigates hybrid quantum-classical vision architectures, with a focus on hybrid quantum-classical convolutional neural networks and hybrid quantum-classical vision transformers. These hybrid models explore both quantum pre-processing and post-processing of data, respectively, where quantum circuits are strategically integrated into the data pipeline to enhance model performance. Our results suggest that these hybrid models can enhance accuracy and computational efficiency in vision-related tasks, even with the constraints of current noisy intermediate-scale quantum devices.

Computing-intensive semantic communication emphasizes context, enabling the extraction of task-specific semantics from the source data and the reconstruction of the intended meaning at the destination. In industrial cyber-physical systems (CPSs), this approach can optimize automation processes while minimizing communication overhead with efficient bandwidth use in environments where machines, sensors, and controllers must communicate frequently. By integrating quantum communication with computing-empowered semantic methods, we can achieve unprecedented efficiency and security in task-oriented data transmission, effectively safeguarding against eavesdropping and other attacks. This paper presents a controlled quantum semantic communication (QSC) framework that leverages semantic extraction for anomaly detection in industrial CPS networks and employs controlled quantum communication to send the data securely with high semantic fidelity. A machine learning model extracts semantic information from images as the hull point data representing defective regions as pixel points. This data is then transmitted with high fidelity using quantum communication with controlled quantum state preparation. We use discrete- and continuous-variable states to simulate quantum binary phase-shift keying (BPSK) and $M$-ary pulse position modulation ($M$-PPM), respectively. At the receiver, these quantum states are measured using optimal quantum decision-making and converted back into the hull point data, thereby generating the anomaly map. This map is overlaid on a template image to highlight defect positions, which can be used for industrial quality control. Furthermore, we simulate the controlled QSC framework (BPSK and $M$-PPM) across a diverse set of anomaly detection examples and evaluate the QSC performance in industrial CPS networks.

Multiple-input multiple-output (MIMO) communication has significantly enhanced classical telecommunication systems by utilizing multiple transmission paths to improve data rate and reliability. Recent studies suggest that MIMO architectures could similarly benefit quantum communications in lossy environments. In this work, we examine MIMO quantum communication in correlated pure-loss channels, where we model losses as probabilistic erasures. Using symmetric quantum cloning in a 2 × 2 MIMO setup, we derive average fidelity expressions to evaluate the performance under varying correlation strength of losses. Our results indicate that MIMO setups provide fidelity benefits in low-correlation scenarios, but these advantages diminish as correlation increases.

Complex optimization problems, such as traffic routing and electric vehicle (EV) charging scheduling, are becoming increasingly challenging for intelligent transportation systems (ITSs), in particular as computational resources are limited and network conditions evolve frequently. This paper explores a quantum computing approach to address these issues by proposing a hybrid quantum-classical (HQC) workflow that leverages the variational quantum eigensolver (VQE), an algorithm particularly well suited for execution on noisy intermediate-scale quantum (NISQ) hardware. To this end, the EV charging scheduling and traffic routing problems are both reformulated as binary optimization problems and then encoded into Ising Hamiltonians. Within each VQE iteration, a parametrized quantum circuit (PQC) is prepared and measured on the quantum processor to evaluate the Hamiltonian’s expectation value, while a classical optimizer—such as COBYLA, SPSA, Adam, or RMSProp—updates the circuit parameters until convergence. In order to find optimal or nearly optimal solutions, VQE uses PQCs in combination with classical optimization algorithms to iteratively minimize the problem Hamiltonian. Simulation results exhibit that the VQE-based method increases the efficiency of EV charging coordination and improves route selection performance. These results demonstrate how quantum computing will potentially advance optimization algorithms for next-generation ITSs, representing a practical step toward quantum-assisted mobility solutions.

Quantum entanglement is a unique phenomenon of quantum mechanics, which has no classical counterpart and gives quantum systems their advantage in computing, communication, sensing, and metrology. In quantum sensing and metrology, utilizing an entangled probe state enhances the achievable precision more than its classical counterpart. Noise in the probe state preparation step can cause the system to output unentangled states, which might not be resourceful. Hence, an effective method for the detection and classification of tripartite entanglement is required at that step. However, current mathematical methods cannot robustly classify multiclass entanglement in tripartite quantum systems, especially in the case of mixed states. In this paper, we explore the utility of artificial neural networks for classifying the entanglement of tripartite quantum states into fully separable, biseparable, and fully entangled states. We employed Bell’s inequality for the dataset of tripartite quantum states and train the deep neural network for multiclass classification. This entanglement classification method is computationally efficient due to using a small number of measurements. At the same time, it also maintains generalization by covering a large Hilbert space of tripartite quantum states.