The growing demand for energy-efficient, high-performance AI systems has led to increased attention on alternative computing platforms (e.g., photonic, neuromorphic) due to their potential to accelerate learning and inference. However, integrating such physical components into deep learning pipelines remains challenging, as physical devices often offer limited expressiveness, and their non-differentiable nature renders on-device backpropagation difficult or infeasible. This motivates the development of hybrid architectures that combine digital neural networks with reconfigurable physical layers, which effectively behave as black boxes. In this work, we present a framework for the end-to-end training of such hybrid networks. This framework integrates stochastic zeroth-order optimization for updating the physical layer's internal parameters with a dynamic low-rank surrogate model that enables gradient propagation through the physical layer. A key component of our approach is the implicit projector-splitting integrator algorithm, which updates the lightweight surrogate model after each forward pass with minimal hardware queries, thereby avoiding costly full matrix reconstruction. We demonstrate our method across diverse deep learning tasks, including: computer vision, audio classification, and language modeling. Notably, across all modalities, the proposed approach achieves near-digital baseline accuracy and consistently enables effective end-to-end training of hybrid models incorporating various non-differentiable physical components (spatial light modulators, microring resonators, and Mach-Zehnder interferometers). This work bridges hardware-aware deep learning and gradient-free optimization, thereby offering a practical pathway for integrating non-differentiable physical components into scalable, end-to-end trainable AI systems.

Quantum communication is poised to become a foundational element of next-generation networking, offering transformative capabilities in security, entanglement-based connectivity, and computational offloading. However, the classical OSI model-designed for deterministic and error-tolerant systems-cannot support quantum-specific phenomena such as coherence fragility, probabilistic entanglement, and the no-cloning theorem. This paper provides a comprehensive survey and proposes an architectural redesign of the OSI model for quantum networks in the context of 7G. We introduce a Quantum-Converged OSI stack by extending the classical model with Layer 0 (Quantum Substrate) and Layer 8 (Cognitive Intent), supporting entanglement, teleportation, and semantic orchestration via LLMs and QML. Each layer is redefined to incorporate quantum mechanisms such as enhanced MAC protocols, fidelity-aware routing, and twin-based applications. This survey consolidates over 150 research works from IEEE, ACM, MDPI, arXiv, and Web of Science (2018-2025), classifying them by OSI layer, enabling technologies such as QKD, QEC, PQC, and RIS, and use cases such as satellite QKD, UAV swarms, and quantum IoT. A taxonomy of cross-layer enablers-such as hybrid quantum-classical control, metadata-driven orchestration, and blockchain-integrated quantum trust-is provided, along with simulation tools including NetSquid, QuNetSim, and QuISP. We present several domain-specific applications, including quantum healthcare telemetry, entangled vehicular networks, and satellite mesh overlays. An evaluation framework is proposed based on entropy throughput, coherence latency, and entanglement fidelity. Key future directions include programmable quantum stacks, digital twins, and AI-defined QNet agents, laying the groundwork for a scalable, intelligent, and quantum-compliant OSI framework for 7G and beyond.

Neural network (NN)-based end-to-end (E2E) communication systems, in which each system component may consist of a portion of a neural network, have been investigated as potential tools for developing artificial intelligence (Al)-native E2E systems. In this paper, we propose an NN-based bitwise receiver that improves computational efficiency while maintaining performance comparable to baseline demappers. Building on this foundation, we introduce a novel symbol-wise autoencoder (AE)-based E2E system that jointly optimizes the transmitter and receiver at the physical layer. We evaluate the proposed NN-based receiver using bit-error rate (BER) analysis to confirm that the numerical BER achieved by NN-based receivers or transceivers is accurate. Results demonstrate that the AE-based system outperforms baseline architectures, particularly for higher-order modulation schemes. We further show that the training signal-to-noise ratio (SNR) significantly affects the performance of the systems when inference is conducted at different SNR levels.

The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and computational hardware. Incorporating complex physical events in networks as fixed, efficient computation modules can address this demand by decreasing the complexity of trainable layers. Here, we utilize ultrashort pulse propagation in multimode fibers, which perform large-scale nonlinear transformations, for this purpose. Training the hybrid architecture is achieved through a neural model that differentiably approximates the optical system. The training algorithm updates the neural simulator and backpropagates the error signal over this proxy to optimize layers preceding the optical one. Our experimental results achieve state-of-the-art image classification accuracies and simulation fidelity. Moreover, the framework demonstrates exceptional resilience to experimental drifts. By integrating low-energy physical systems into neural networks, this approach enables scalable, energy-efficient AI models with significantly reduced computational demands.

This paper proposes a cyber-physical architecture for the secured social operation of isolated hybrid microgrids (HMGs). On the physical side of the proposed architecture, an optimal scheduling scheme considering various renewable energy sources (RESs) and fossil fuel-based distributed generation units (DGs) is proposed. Regarding the cyber layer of MGs, a wireless architecture based on low range wide area (LORA) technology is introduced for advanced metering infrastructure (AMI) in smart electricity grids. In the proposed architecture, the LORA data frame is described in detail and designed for the application of smart meters considering DGs and ac-dc converters. Additionally, since the cyber layer of smart grids is highly vulnerable to cyber-attacks, t1his paper proposes a deep-learning-based cyber-attack detection model (CADM) based on bidirectional long short-term memory (BLSTM) and sequential hypothesis testing (SHT) to detect false data injection attacks (FDIA) on the smart meters within AMI. The performance of the proposed energy management architecture is evaluated using the IEEE 33-bus test system. In order to investigate the effect of FDIA on the isolated HMGs and highlight the interactions between the cyber layer and physical layer, an FDIA is launched against the test system. The results showed that a successful attack can highly damage the system and cause widespread load shedding. Also, the performance of the proposed CADM is examined using a real-world dataset. Results prove the effectiveness of the proposed CADM in detecting the attacks using only two samples.

The recognition or understanding of the scenes observed with a SAR system requires a broader range of cues, beyond the spatial context. These encompass but are not limited to: imaging geometry, imaging mode, properties of the Fourier spectrum of the images or the behavior of the polarimetric signatures. In this paper, we propose a change of paradigm for explainability in data science for the case of Synthetic Aperture Radar (SAR) data to ground the explainable AI for SAR. It aims to use explainable data transformations based on well-established models to generate inputs for AI methods, to provide knowledgeable feedback for training process, and to learn or improve high-complexity unknown or un-formalized models from the data. At first, we introduce a representation of the SAR system with physical layers: i) instrument and platform, ii) imaging formation, iii) scattering signatures and objects, that can be integrated with an AI model for hybrid modeling. Successively, some illustrative examples are presented to demonstrate how to achieve hybrid modeling for SAR image understanding. The perspective of trustworthy model and supplementary explanations are discussed later. Finally, we draw the conclusion and we deem the proposed concept has applicability to the entire class of coherent imaging sensors and other computational imaging systems.

Secure digital wireless communication underwater has become a key issue as maritime operations shift towards employing a heterogeneous mix of robotic assets and as the security of digital systems becomes challenged across all domains. At the same time, a proliferation of underwater signal coding and physical layer options are delivering greater bandwidth and flexibility, but mostly without the standards necessary for interoperability. We address here an essential requirement for security, namely a confirmation of asset identities also known as authentication. We propose, implement, verify and validate an authentication protocol based on the first digital underwater communications standard. Our scheme is applicable primarily to AUVs operating around offshore oil and gas facilities, but also to other underwater devices that may in the future have acoustic modems. It makes communication including command and control significantly more secure and provides a foundation for the development of more sophisticated security mechanisms.

Federated Learning (FL) over wireless multi-hop edge computing networks, i.e., multi-hop FL, is a cost-effective distributed on-device deep learning paradigm. This paper presents FedEdge simulator, a high-fidelity Linux-based simulator, which enables fast prototyping, sim-to-real code, and knowledge transfer for multi-hop FL systems. FedEdge simulator is built on top of the hardware-oriented FedEdge experimental framework with a new extension of the realistic physical layer emulator. This emulator exploits trace-based channel modeling and dynamic link scheduling to minimize the reality gap between the simulator and the physical testbed. Our initial experiments demonstrate the high fidelity of the FedEdge simulator and its superior performance on sim-to-real knowledge transfer in reinforcement learning-optimized multi-hop FL.

Large space structures, such as telescopes and spacecraft, should ideally be assembled directly in space, as they are difficult or impossible to launch from Earth as a single piece. In several cases, however, assembling these technologies manually in space is either highly expensive or unfeasible. In recent years, roboticists have thus been trying to develop systems that could be used to automatically assemble structures in space. To simplify this assembly process, space structures could have a modular design, which essentially means that they are comprised of different building blocks or modules that can be shifted to create different shapes or forms. Researchers at the German Aerospace Center (DLR) and Technische Universität München (TUM) have recently developed an autonomous planner that could be used to assemble reconfigurable structures directly in space.

An illuminated 5G sign hangs behind a weave of electronic cables on the opening day of the MWC ... [ ] Barcelona in Barcelona, Spain, on Monday, Feb. 25, 2019. At the wireless industry's biggest conference, over 100,000 people are set to see the latest innovations in smartphones, artificial intelligence devices and autonomous drones exhibited by more than 2,400 companies. At the core of this evolutionary step is the use of machine learning algorithms. The ability to be more dynamic with real-time network optimization capabilities such as resource loading, power budget balancing and interference detection is what made networks "smart" in the 4G era. While there are many uses of machine learning across all layers of a 5G network from the physical layer through to the application layer, the base station is emerging as a key application for machine learning.