Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Signals and communication technology

Hybrid Quantum–Classical Learning Architectures for 6G/7G Edge Intelligence

Anushikha Singh, Inam Ul Haq, Nehul Jain, Rohit Kumar, Mushtaq Ahmad Rather, Faheem Syeed Masoodi

Published Jan 1, 2026• 1 citation
Publisher
DOI
10.1007/978-981-95-1683-4_14

Related papers

Quantum Convolutional Neural Networks for Intelligent Spectrum Management in 6G/7G

Inam Ul Haq, Anushikha Singh, Nehul Jain +2 more

Signals and communication technology•Jan 1, 2026•0 citations

AI-integrated quantum networks for 6G

Nancy Alshaer, Tawfik Ismail

CRC Press eBooks•Feb 19, 2025•0 citations

Efficient integration of quantum machine learning techniques into devices with limited computing resources for edge computing in modern 6G networks

Ηρακλής Γ. Τσέλκας

The subject of this bachelor thesis was the investigation and proposal of efficient methods for integrating Quantum Machine Learning (QML) techniques into Edge Computing environments of modern 6G networks.The primary objective of the study was to overcome the computational and energy constraints faced by devices at the network edge when executing traditional artificial intelligence algorithms.In the context of this work, the 6G network architecture was analyzed, and the requirements for real-time sensor data processing were identified.The core principles of quantum computing were studied, and modern QML algorithms were evaluated, focusing on hybrid classical-quantum models compatible with NISQ-era devices.The methodology followed was based on the design of Parameterized Quantum Circuits (PQCs), applying optimization techniques such as angle encoding and circuit pruning to minimize circuit depth and power consumption.To evaluate the proposed architecture, simulations were conducted using the PennyLane and Qiskit frameworks.The results demonstrated that the use of quantum co-processors at the network edge can offer a significant reduction in the number of required parameters compared to classical neural networks, while ensuring high accuracy in data classification.In conclusion, the thesis highlighted that quantum computing can be a catalyst for the sustainability of Edge AI in 6G, providing an energy-efficient solution for devices with limited computational resources.

•Jan 1, 2026•0 citations

Quantum Machine Learning: Hybrid System of Quantum and Classical Computing

Lian Peng, Meikang Qiu, Chong Li +1 more

Lecture notes in computer science•Jan 1, 2025•3 citations

Quantum Protocol Architectures and Secure Control Frameworks For 7G+ Networks: Standards, Synchronization, Use Cases, and Challenges

Shakil Ahmed, Ibrahim Almazyad, Ashfaq Khokhar

ABSTRACT Quantum‐native communication systems are reshaping secure, programmable, and coherence‐aware networking beyond the classical paradigm. As intelligent physical infrastructures, ranging from unmanned aerial vehicle swarms to satellite Quantum Key Distribution (QKD) platforms, demand trust, synchronization, and ultra‐reliability, conventional protocol designs struggle to preserve entanglement and coherence while coordinating control logic across hybrid domains. This paper surveys layered protocol architectures and secure control frameworks designed for post‐6G and emerging 7G+ quantum‐enabled networks. Quantum‐classical hybrid denotes networks in which quantum links used for entanglement distribution or QKD interoperate with classical links and protocols within a unified communication fabric. We develop a taxonomy of the protocol stack, spanning the entanglement‐aware physical layer to the service‐level agreement (SLA)‐driven application layer, and covering representative technologies such as Q‐SDN (quantum software‐defined networking), quantum transmission Control Protocol, hybrid QKD and PQC (post‐quantum cryptography) integration, and intent‐driven orchestration through large language model agents. We revisit security using blockchain‐based trust anchors and fidelity‐aware metadata frameworks, and examine quantum synchronization and teleportation‐resilient session‐control mechanisms for preserving inter‐digital‐twin coherence. Through a broad review of architectural blueprints, protocol proposals, use cases, and simulation‐driven models, this paper positions quantum‐native protocol stacks as a foundation for secure, resilient, and intelligent communication systems.

Advanced Quantum Technologies•May 1, 2026•2 citations

Quantum-Enhanced Learning Framework for Intelligent and AI-Native 6G Wireless Networks

Muhammad Bilal Akram Dastagir, Rakesh Saini, Omer Tariq +4 more

The recent convergence of 6G wireless systems and Tiny Machine Learning (TinyML) has driven the need for on-device intelligence in edge networks, where ultra-low latency, stringent energy budgets, and tight compute constraints demand novel architectures. Lightweight deep models efficiently extract local patterns but fail to capture global dependencies, while attention mechanisms do so at the expense of energy and computational cost. To bridge this gap, we introduce Quantumer, a hybrid TinyML--quantum framework that integrates multi-scale dilated convolutions and scaled dot-product attention within a lightweight transformer architecture, employing a two-stage transfer learning pipeline from Quantum Pre-Training (Quantumer-Q) to Classical Fine-Tuning (Quantumer-C). We also present QuantiblentLayer, a four-qubit variational circuit that maps compact traffic representations into measurement-based Hilbert-space features using trainable rotations and cyclic entangling operations. The circuit is used only during offline pre-training as a nonlinear embedding teacher and is removed before Quantumer-C deployment, leaving a fully classical inference model without runtime quantum execution. By transferring these quantum-assisted embeddings into an energy-efficient, lightweight transformer, Quantumer achieves strong detection performance with minimal compute and memory overhead on resource-constrained edge devices. The intrusion detection system (IDS) is used as a case study and evaluated on the Edge-IIoTset, TON IoT, and WUSTL-IIoT-2021 datasets. Quantumer-Q achieves competitive compact-model performance with 105.86K parameters, 0.4038 MB memory usage, 0.5525 MB model size, and 5.5646 MFLOPs; the INT8 Raspberry Pi 4 deployment obtains 16.8413 ms latency with a 0.6493 MB footprint. These results support training-time quantum-assisted representation learning for compact edge-deployable IDS.

quant-pharXiv:2609.06814•Sep 8, 2026•0 citations
The subject of this bachelor thesis was the investigation and proposal of efficient methods for integrating Quantum Machine Learning (QML) techniques into Edge Computing environments of modern 6G networks.The primary objective of the study was to overcome the computational and energy constraints faced by devices at the network edge when executing traditional artificial intelligence algorithms.In the context of this work, the 6G network architecture was analyzed, and the requirements for real-time sensor data processing were identified.The core principles of quantum computing were studied, and modern QML algorithms were evaluated, focusing on hybrid classical-quantum models compatible with NISQ-era devices.The methodology followed was based on the design of Parameterized Quantum Circuits (PQCs), applying optimization techniques such as angle encoding and circuit pruning to minimize circuit depth and power consumption.To evaluate the proposed architecture, simulations were conducted using the PennyLane and Qiskit frameworks.The results demonstrated that the use of quantum co-processors at the network edge can offer a significant reduction in the number of required parameters compared to classical neural networks, while ensuring high accuracy in data classification.In conclusion, the thesis highlighted that quantum computing can be a catalyst for the sustainability of Edge AI in 6G, providing an energy-efficient solution for devices with limited computational resources.
ABSTRACT Quantum‐native communication systems are reshaping secure, programmable, and coherence‐aware networking beyond the classical paradigm. As intelligent physical infrastructures, ranging from unmanned aerial vehicle swarms to satellite Quantum Key Distribution (QKD) platforms, demand trust, synchronization, and ultra‐reliability, conventional protocol designs struggle to preserve entanglement and coherence while coordinating control logic across hybrid domains. This paper surveys layered protocol architectures and secure control frameworks designed for post‐6G and emerging 7G+ quantum‐enabled networks. Quantum‐classical hybrid denotes networks in which quantum links used for entanglement distribution or QKD interoperate with classical links and protocols within a unified communication fabric. We develop a taxonomy of the protocol stack, spanning the entanglement‐aware physical layer to the service‐level agreement (SLA)‐driven application layer, and covering representative technologies such as Q‐SDN (quantum software‐defined networking), quantum transmission Control Protocol, hybrid QKD and PQC (post‐quantum cryptography) integration, and intent‐driven orchestration through large language model agents. We revisit security using blockchain‐based trust anchors and fidelity‐aware metadata frameworks, and examine quantum synchronization and teleportation‐resilient session‐control mechanisms for preserving inter‐digital‐twin coherence. Through a broad review of architectural blueprints, protocol proposals, use cases, and simulation‐driven models, this paper positions quantum‐native protocol stacks as a foundation for secure, resilient, and intelligent communication systems.
The recent convergence of 6G wireless systems and Tiny Machine Learning (TinyML) has driven the need for on-device intelligence in edge networks, where ultra-low latency, stringent energy budgets, and tight compute constraints demand novel architectures. Lightweight deep models efficiently extract local patterns but fail to capture global dependencies, while attention mechanisms do so at the expense of energy and computational cost. To bridge this gap, we introduce Quantumer, a hybrid TinyML--quantum framework that integrates multi-scale dilated convolutions and scaled dot-product attention within a lightweight transformer architecture, employing a two-stage transfer learning pipeline from Quantum Pre-Training (Quantumer-Q) to Classical Fine-Tuning (Quantumer-C). We also present QuantiblentLayer, a four-qubit variational circuit that maps compact traffic representations into measurement-based Hilbert-space features using trainable rotations and cyclic entangling operations. The circuit is used only during offline pre-training as a nonlinear embedding teacher and is removed before Quantumer-C deployment, leaving a fully classical inference model without runtime quantum execution. By transferring these quantum-assisted embeddings into an energy-efficient, lightweight transformer, Quantumer achieves strong detection performance with minimal compute and memory overhead on resource-constrained edge devices. The intrusion detection system (IDS) is used as a case study and evaluated on the Edge-IIoTset, TON IoT, and WUSTL-IIoT-2021 datasets. Quantumer-Q achieves competitive compact-model performance with 105.86K parameters, 0.4038 MB memory usage, 0.5525 MB model size, and 5.5646 MFLOPs; the INT8 Raspberry Pi 4 deployment obtains 16.8413 ms latency with a 0.6493 MB footprint. These results support training-time quantum-assisted representation learning for compact edge-deployable IDS.