Unmanned aerial vehicle (UAV) communication systems usually operate in harsh scenarios, which require accurate information about the topology and wireless channel to achieve the desired transmission performance. Therefore, when millimeter-wave (mmWave) communication with its intrinsic Line-of-Sight (LoS) condition is adopted, accurate target localization is essential to determine the spatial relationship between the UAV and the grounded receivers (Rxs). In this article, a computer-vision (CV)-aided jointly optimization scheme of flight trajectory and power allocation is designed for mmWave UAV communication systems by utilizing the visual information captured via cameras equipped at the UAV. Compared with traditional schemes, the implementation cost and overhead can be greatly saved as no radio frequency transmissions are required in the proposed localization scheme. In addition, the transmit power at the UAV is jointly optimized with its flight trajectory in two different cases. Finally, simulation results are presented to demonstrate the efficiency of the proposed schemes.

The rapid expansion of Low Earth Orbit (LEO) satellite constellations has brought significant spectrum management challenges, including spectrum scarcity and complex interference issues. Traditional algorithms and prior Artificial Intelligence (AI) methods fail to meet LEO’s demands for managing extreme dynamics, massive scale, and multi-objective optimization. This paper introduces an innovative Large Language Model (LLM) framework for intelligent spectrum sharing and dynamic resource allocation in satellite-terrestrial down-link systems. First, we established a geometric model for satellite-terrestrial down-link communication, and accurately derived the statistical distribution function of satellites within the space enclosed by a specific orbital line by combining the stochastic geometry theory. Under this geometric model, a communication scenario was introduced, and an adaptive modulation transmission mechanism based on orthogonal frequency division multiplexing signals was designed. Then, the system combines the real-time spectrum sensing results with the natural language description of the quality of service of multi-service data using prompt engineering techniques, and delivers the comprehensive information to the LLM for resource allocation and generation of a transmission scheme. Finally, the resource allocation and transmission scheme determined by the LLM is applied to the established communication model, and the system performance is comprehensively evaluated by analyzing indicators such as outage probability, system throughput, and transmission and waiting delays. Primary contributions include novel dynamic service-to-strategy generation, an LLM-centric prompt-driven architecture, and a new paradigm that positions the LLM as an intelligent “spectrum orchestration brain” for complex global LEO resource management. Collectively, these advancements enhance spectrum utilization intelligence, adaptability, and efficiency, offering a transformative approach to overcome the limitations of prior methods in demanding LEO environments.

Achieving secure communication with a low probability of detection (covertness) is critical yet challenging, particularly when employing practical digital modulations that can compromise the statistical indistinguishability assumed in theoretical models. This paper introduces a novel end-to-end framework leveraging digitally modulated covert signal modeling, obfuscation, and deep learning to attain simultaneous covertness and reliability. Firstly, we propose a novel approach to covert performance evaluation for modulated covert signals against detection. To address the deteriorated covertness considering modulation schemes, we further propose generating Gaussianized camouflage signals via a multi-stage transmitter pipeline encompassing spreading, jitter, filtering, and non-linear transformations, designed to mimic noise statistics effectively. At the receiver, a specialized deep learning architecture, CovertSyncNet, performs robust joint dynamic synchronization and symbol recovery. This receiver incorporates dedicated components to precisely estimate time-varying chip offsets and invert the complex, nonlinear distortions inherent in the camouflaged signal, enabling accurate demodulation. Extensive simulations rigorously validate our approach, demonstrating that high reliability is maintained despite the heavy camouflage. Concurrently, enhanced covertness is confirmed through metrics indicating low statistical distinguishability from Gaussian noise. This work highlights the significant potential of deep learning to bridge the gap between theory and practice, realizing communication systems that are simultaneously reliable, secure, and highly covert, even under realistic operational conditions.

Traditional antenna systems, constrained by static architectures, are increasingly unable to support the reliable, flexible, and resilient communications demanded in dynamic environments. This article introduces the Distributed Movable Antenna System (DMAS), a novel architecture that combines local antenna mobility with distributed Remote Movable Antenna Units (RMAUs) to exploit spatial degrees of freedom (DoF) across large geographical areas. By extending coverage through distributed deployment and enhancing channel quality via antenna adjustments, DMAS enables more adaptive and robust wireless transmissions under intricate propagation conditions. In this article, we initially introduce a representative architecture of DMAS. To illustrate the advantages of DMAS, we compare it to existing antenna systems and propose its potential application scenarios. We then examine the main design considerations, including RMAU deployment, synchronization, channel estimation, and movable antenna optimization. The simulation results demonstrate the improvements in signal strength and system capacity with DMAS. Furthermore, a general optimization framework is outlined and discussed to guide the optimization of DMAS. Ultimately, potential integration prospects are investigated, significant deployment obstacles, alongside viable solutions, are addressed for the practical implementation of DMAS.

Given tremendously growing security and privacy concerns, there is a substantial surge in demand for covert communication techniques. Traditional methods, constrained by static configurations and an inability to leverage historical data, suffer from inefficiencies in resource utilization, vulnerability to evolving threats, and limited adaptability to interference. This article introduces a Generative Artificial Intelligence (GAI)-driven framework to overcome such limitations, integrating advanced models such as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Generative Diffusion Models (GDMs) into covert communication systems. By employing unsupervised learning, the framework dynamically optimizes transmission parameters—including power allocation, modulation schemes, and frequency hopping—in real time, enabling adaptive responses to channel conditions and historical patterns. Through this optimization, the proposed approach enhances security via unpredictable transmission patterns, reduces bit error rates with optimized modulation and coding schemes, and strengthens resistance to interference and interception through noise-like signal generation. In addition to these advancements, the paper identifies key challenges and further outlines future directions. This work underscores GAI’s transformative potential in balancing concealment, efficiency, and adaptability for next-generation covert communication systems.

Due to the complexity of airborne remote sensing scenes, strong background and noise interference, positive and negative sample imbalance, and multiple ship scales, ship detection is a critical and challenging task in remote sensing. This work proposes an end-to-end anchor-free oriented ship detector (AF-OSD) framework based on a multi-scale dense-point rotation Gaussian heatmap (MDP-RGH) to tackle these aforementioned challenges. First, to solve the sample imbalance problem and suppress the interference of negative samples such as background and noise, the oriented ship is modeled via the proposed MDP-RGH according to its shape and direction to generate ship labels with more accurate information, while the imbalance between positive and negative samples is adaptively learned for the ships with different scales. Then, the AF-OSD based on MDP-RGH is further devised to detect the multi-scale oriented ship, which is the accurate identification and information extraction for multi-scale vessels. Finally, a multi-task object size adaptive loss function is designed to guide the training process, improving its detection quality and performance for multi-scale oriented ships. Simulation results show that extensive experiments on HRSC2016 and DOTA ship datasets reveal that the proposed method achieves significantly outperforms the compared state-of-the-art methods.