Text-to-3D generation has made significant progress in terms of fidelity and geometric consistency. However, current methods still struggle to generate complex attributes from the text prompts. We thus present RainbowDreamer, a three-stage framework that builds up the semantic controls to generate attribute-consistent 3D Gaussian Splattings (3DGS). In detail, in the first stage, we optimize a 3DGS for geometry reference by removing the attribute prompts optimized by a hybrid stable diffusion and multi-view diffusion models with a view-dependent rescaling strategy. Then, utilizing the geometry of this reference 3DGS, we optimize their color only via a diffusion-based full prompt lifting, where the attention restriction between two stages is utilized to measure the semantic consistency. Finally, we further introduce a refinement stage for the overall quality of the 3D assets via Bootstrapped Score Distillation. We evaluate the generated 3D assets from multiple aspects using both CLIP similarity and complex vision language model understanding abilities. Results demonstrate that RainbowDreamer achieves state-of-the-art performance in both quantitative and qualitative evaluations.

Aero-engines, as pivotal components in aviation, demand robust prognostics and health management (PHM) to mitigate degradation risks and optimize maintenance amid complex operational stresses. Conventional scheduled strategies often yield inefficiencies, prompting the integration of digital twins (DTs) for enhanced predictive capabilities. This study introduces a comprehensive DT-based aero-engine health management framework, stratified into physical, data, model, and application layers, augmented by a Unity-driven 3D visualization module for immersive virtual-real interactions. The physical layer captures real-time sensor data from turbofan components, feeding into the data layer for preprocessing, fusion, and lifecycle storage. The model layer employs a novel physically decoupled multi- branch long short-term memory (LSTM) network with attention fusion, segmenting sensor features (e.g., temperature, pressure) into specialized branches to discern degradation channels while dynamically weighting salient contributions. Outputs manifest in the application layer via interactive dashboards for RUL fore- casting, anomaly alerts, and maintenance simulations. Validated on the N-CMAPSS DS01 dataset, the model attains an R2 of 0.9376 and RMSE of 5.76 cycles, outperforming single-branch LSTM (R2 = 0.7306) and Transformer (R2 = 0.7810) baselines by leveraging physical priors for superior trend capture and interpretability. Unity integration enables real-time 3D mapping of predictions, fostering user-centric diagnostics. This framework advances PHM by harmonizing deep learning with DTs, boosting accuracy, usability, and decision-making in civil aviation. Limitations in multi-condition scenarios underscore avenues for future uncertainty modeling and lightweight adaptations. Note to Practitioners This digital twin (DT) framework advances aero-engine prognostics and health management (PHM) by delivering interpretable remaining useful life (RUL) predictions to combat inefficiencies in traditional scheduled maintenance, which costs aviation billions in downtime and overhauls. Structured across physical, data, model, and application layers, it processes real- time turbofan sensor data (e.g., temperature, pressure) to support proactive decision-making. The core multi-branch LSTM with attention fusion decouples features by physics (e.g., temperature branches), dynamically weighting degradation signals, such as turbine exhaust, for superior accuracy and transparency. On the N-C MAPSS DS01 dataset, it reaches R2 = 0.9376 and RMSE = 5.76 cycles, surpassing the single-branch LSTM (R2 = 0.7306) and Transformer (R2 = 0.7810) baselines by 20–28%. Benefits include 10-15% longer on-the-wing times and reduced inspections. Unity 3D visualization maps RUL onto interactive models, enabling engineers to identify anomalies, simulate maintenance, and receive alerts, bridging AI to actionable insights without requiring expertise. Deployable via edge cloud for avionics, it scales to variable flight sizes; future work will add uncertainty modeling for noisy data. This empowers predictive stewardship, boosting safety and economics.

On unlicensed spectrum, the beam scanning in directional listen before talk (LBT) channel access is similar to the beam training procedure adopted for channel estimation before data transmission. Therefore, repeating these operations not only increases signalling overhead but also wastes limited resources. To address this issue, this paper proposes an efficient data transmission strategy that combines the two similar aforementioned steps. Considering the limited capacity of each beam, the optimal beam pairing problem between the transmitter and the receiver is formulated as a matching game problem and solved by means of the Gale-Shapley algorithm. Finally, the results validate the effectiveness of the proposed mechanism in reducing the complexity of beam search, minimizing the signalling overhead, and optimizing the system capacity.

With their high mobility and ease of deployment, unmanned aerial vehicle (UAV)-assisted communication systems have emerged as a prominent area of academic research and a cornerstone technology for Sixth-Generation (6G) mobile communication networks. This paper investigates a multi-UAV downlink wireless communication system in which users exhibit random movement on the ground. To maximize the sum-rate of all users over the observation period, we propose a joint optimization framework that integrates user association, UAV 3D trajectory design, and power allocation, while addressing channel estimation across different timescales. In the long timescale, we model the UAV-user connections as a graph and utilize a graph neural network to jointly optimize user association and UAV trajectories. In the short timescale, we deploy a deep unfolding network for efficient channel estimation and power allocation. Simulation results validate the effectiveness of the proposed approach, showcasing significant performance improvements.

In decentralized learning systems over wireless device-to-device (D2D) networks, training latency is a key metric that needs to be minimized by link selection and resource allocation, thereby accelerating model training. However, it may cause large computational complexity in general. To tackle the challenge, this paper proposes a graph neural network (GNN)-based algorithm to minimize the training latency. Under modeling the D2D network as a graph, the link selection and resource allocation can be efficiently obtained based on the local computing power and link quality. By the constraint on the network connectivity, the training latency can be significantly reduced while guaranteeing accuracy with a low complexity. The simulation results demonstrate that the GNN-based approach outperforms traditional approaches, offering superior scalability and robustness in heterogeneous large-scale D2D networks.

The millimeter wave (mmWave) communication becomes a key enabler for the future Internet of Things (IoT) due to its capability for supporting high rate and low-latency traffic. However, beamforming in the mmWave band faces issues of low efficiency since the narrow beam of mmWave devices would increase the search delay and overhead. Inspired by this, we utilize localization over sub-6 GHz band to assist the mmWave base station in performing fast and robust adaptive beamforming (RABF). Different from existing works, we focus on the indoor scenario and consider the effects of several practical issues, including localization errors and hardware defects. Specifically, a novel two-step access scheme is proposed. During the first step, we design a novel localization method customized for indoor scenarios, jointly considering the time of flight and angle of arrival. The localization error is further analyzed to determine the mmWave scanning angle and an optimal beamwidth expression is derived in closed-form to maximize system throughput with the considerations of the search delay. Moreover, considering the mismatch of the steering vector caused by the hardware defects, we propose an RABF method in closed-form. Simulation results demonstrate that the proposed scheme can effectively reduce the search delay and realize robust beamforming to enhance the mmWave communication performance.

WiFi-based gesture recognition (WGR) has emerged as a promising technology due to its potential for integration with communication systems under the concept of integrated sensing and communication (ISAC). However, current WGR systems face two primary challenges: limited scalability for recognizing new gestures and poor compatibility with ISAC. These systems typically require extensive data collection and retraining for each new gesture and struggle to handle the dimensional variability of channel state information (CSI) caused by fluctuating data traffic in communication networks. To overcome these limitations, we introduce OneSense, a one-shot WGR system designed for seamless integration with communication systems. OneSense designs a data enrichment technique based on the law of signal propagation to generate virtual gestures. Based on enriched dataset, OneSense leverages an aug-meta learning (AML) framework to facilitate efficient and scalable FSL. OneSense also incorporates a data cropping strategy to enhance gesture feature prominence and a dynamic size-adaptive backbone model that ensures compatibility with CSI samples exhibiting dimensional inconsistencies. Experimental results show that OneSense achieves over 94% accuracy in one-shot gesture recognition. A case study further illustrates its effectiveness in ISAC contexts. Furthermore, our proposed AML framework reduces pre-training latency by more than 86% compared to conventional meta-learning approaches.

External disks (henceforth referred to as disks) are commonly used data storage peripherals for hosts. Verifying the legitimacy of these disks is essential to mitigate security risks, such as privacy breaches and virus propagation, before initiating interactions with a host. To address this challenge, we proposeDiskPrint, a novel replay-resistant, few-shot disk authentication system that relies on unintentional electromagnetic (EM) emanations from the internal components of disks. The core idea ofDiskPrintis that EM signals emitted during data writing operations can reveal unique hardware discrepancies among different disks. Building on electromagnetic theory, we develop a theoretical model that links EM signals to the underlying electronic components of the disk, demonstrating the feasibility of extracting distinctive disk fingerprints from these emanations. We also propose a set of signal enhancement techniques aimed at mitigating EM interface noise and improving the signal-to-noise ratio (SNR) of the EM measurements. To further strengthen the security ofDiskPrint, we introduce a device-agnostic, replay-resistant approach by incorporating randomness into the leaked EM signals. Real-world experiments with 60 disks, spanning both hard disk drives (HDDs) and solid-state drives (SSDs) from seven brands and 14 different models, indicate thatDiskPrintachieves an authentication success rate exceeding 99.6% with only three registration samples. A robustness analysis confirms its stability over time, while a security evaluation shows its resilience against various attack scenarios.

For safety guard and crime prevention, video surveillance systems have been pervasively deployed in many security-critical scenarios, such as the residence, retail stores, and banks. However, these systems could be infiltrated by the adversary and the video streams would be modified or replaced, i.e., under the video forgery attack. The prevalence of Internet of Things (IoT) devices and the emergence of Deepfake-like techniques severely emphasize the vulnerability of video surveillance systems under such attacks. To secure existing surveillance systems, in this paper we propose a vision-WiFi cross-modal video forgery detection system, namelyWiSil. Leveraging a theoretical model based on the principle of signal propagation,WiSilconstructs wave front information of the object in the monitoring area from WiFi signals. With a well-designed deep learning network,WiSilfurther recovers silhouettes from the wave front information. Based on a Siamese network-based semantic feature extractor,WiSilcan eventually determine whether a frame is manipulated by comparing the semantic feature vectors extracted from the video’s silhouette with those extracted from the WiFi’s silhouette. We enhance the basic version ofWiSilFang et al. 2023 by developing a model compression method and a forgery trace localization method. Extensive experiments show thatWiSilachieves 95%$+$accuracy in detecting tampered frames.

Deep mutual learning (DML) is one of the emerging technologies for mobile intelligent applications that has attracted much attention in recent years. To effectively deploy DML at a large scale, in this paper, we propose a novel hierarchical asynchronous deep mutual learning (HADML) system that enables devices to collaborate in model training without the exchange of local datasets. To further improve the learning efficiency, the average energy cost for model exchanging is minimized by jointly optimizing the link scheduling and communication resource allocation. To efficiently solve this problem, the graph neural network and deep unfolding network are employed to obtain the link scheduling and resource allocation, respectively. Finally, the simulation results demonstrate that our proposed algorithm can achieve a balance between knowledge sharing and communication energy consumption.

To satisfy the requirements of many industrial applications, realizing ultrareliable low-latency communication (URLLC) has become one of the major challenges for future wireless networks. This article considers a downlink multiuser multiple-input-single-output (MISO) system in the Internet of Things (IoT) networks, in which a multiantenna base station (BS) serves multiple delay-sensitive IoT users, each equipped with a single antenna. To minimize the overall end-to-end delay, we jointly optimize the beamforming vectors and the packet blocklength to balance the queuing delay and the transmission delay. The problem is formulated as a Markov decision process (MDP), whose optimal solution can be theoretically found. However, the complexity on finding the optimal resource allocation and blocklength selection strategy is prohibitively high for real-system deployments due to the large state and action space. To overcome this issue, we simplify the original problem and develop an iterative algorithm to solve the simplified problem based on the uplink-downlink duality theory. Since solving the simplified problem would result in suboptimal solutions and may degrade the latency performance, we further develop a deep-reinforcement-learning (DRL)-based beamforming and blocklength selection framework to efficiently learn the optimal strategy of the original MDP. Simulation results demonstrate that the proposed algorithms can effectively improve the latency performance compared with the benchmark algorithm.

Recently, deep learning (DL) based semantic communication systems have shown great potential to improve transmission efficiency in various tasks. However, the coexisting mechanism between semantic communications and other services remains unexplored, which limits the application of semantic communications in practical communication systems. In this paper, we propose a dynamic multiplexing and co-scheduling scheme for the semantic and ultra-reliable low-latency communication (URLLC) traffic coexisting systems. In particular, a joint resource allocation and model training problem is formulated, which aims at maximizing the utility of semantic service while satisfying the latency requirement of URLLC traffic. To reduce the computational complexity, the original problem is simplified and decoupled into a joint resource allocation and model selection problem and a robust model training problem. In the resource allocation and model selection phase, the original problem is decomposed into three subproblems and an alternating optimization algorithm is then proposed to obtain the optimal resource allocation result. In the model training phase, a two-stage semantic communication network is designed, which can efficiently mitigate the impact of feature erasure brought by the random arrival of URLLC traffic. Simulation results show that the proposed method can effectively improve the quality of semantic service while satisfying the latency requirement of URLLC traffic.

Deep mutual learning (DML) is one of the most high-profile technologies emerging in the field of machine learning during the past few years. DML has the potential of exchanging knowledge on the premise of ensuring data privacy, while retaining the characteristics of local models. In this paper, we design a novel system named as decentralized mutual learning over unlicensed spectrum (DML-U), which allows neighbor mobile devices to learn from each other via bidirectional device-to-device links over unlicensed spectrum (D2D-U). On this basis, we formulate a non-convex optimization problem for the one-to-one pairing scenario with the goal of minimizing the average communication energy cost for sharing knowledge. We further propose a two-layer iterative algorithm that includes the outer layer based on the enumeration method and the inner layer based on the sum-of-ratios optimization, aiming to find the optimal pairing scheme between devices and obtain the global optimal communication resource allocation scheme, respectively. The numerical results validate the effectiveness of the proposed algorithm in improving the DML performance.

In this paper, we design a novel system named as decentralized mutual learning over unlicensed spectrum (DML-U), where edge devices are allowed to learn from each other via bidirectional device-to-device communications over unlicensed spectrum. We further formulate a non-convex optimization problem to minimize energy consumption and accelerate knowledge sharing with constrained power, bandwidth and transmission latency. Under this context, we propose a two-layer iterative algorithm, which contains an enumeration-based outer layer for the pairing scheme and a sum-of-ratios-based inner layer for obtaining a globally optimal allocation of communication resources. Simulation results verify that our obtained algorithm converges fast and finds efficiently the balance between knowledge sharing and communication energy consumption.

In this paper, a novel decentralized mutual learning (DML) network is designed, where each mobile device can share knowledge with its neighbour devices via bidirectional device-to-device (D2D) communication. We subdivide and discuss mutual learning scenarios, and investigate the user association and resource allocation problems for the one-to-many scenario. With constraints on power, bandwidth and communication latency, we formulate a non-convex optimization problem to minimize the average communication energy consumption for sharing new knowledge. On the basis, a two-layer iterative algorithm is proposed, which consists of an outer layer algorithm based on particle swarm optimisation (PSO) for searching a suitable user association strategy and an inner layer algorithm based on sum-of-ratios optimization for achieving a globally optimal allocation of communication resource. Numerical results are presented to verify the fast convergence and the effectiveness of the proposed algorithm in terms of a trade-off between energy consumption and knowledge sharing efficiency.

Massive data drives the development of machine learning (ML) for a long time. However, at present, data is starting to hinder ML's development. The first reason is that the privacy of data is increasingly valued by the public. Therefore, Federated Learning (FL) has emerged, which realizes model training through distributed computing and centralized aggregation. Second, due to the popularity of FL, edge devices need to store all data, which may quickly occupy the entire storage space of edge devices, resulting in fatal errors. To address these challenges, we proposed a storage-aware joint user scheduling and spectrum allocation algorithm, named FedSUS, to reduce the storage stress of each device and guarantee traditional FL metrics, i.e., learning accuracy and training latency. First, a probabilistic framework is adopted for user scheduling. Second, we introduce a data influence evaluation method to FL and analyze its convergence. Based on this, two problems are formulated to tradeoff the storage resource, the influence of data, and the learning latency and to minimize the transmission latency, respectively. Then, the closed-form results to the above problems are both developed. Finally, FedSUS is validated by using a popular convolutional neural network (CNN) and datasets (CIFAR-10). And numerical results demonstrate that our algorithm can effectively reduce the local data size while keeping (even improving) the learning accuracy as compared with baseline.

Ultra-reliable low-latency communication (URLLC) is essential for future vehicle-to-vehicle (V2V) networks to improve traffic safety and enhance driving experience. Due to the fast-varying channel caused by high mobility, guaranteeing latency and reliability performance of the V2V links is a tremendous challenge. In this paper, we propose a novel resource allocation framework to support ultra-reliable low-latency V2V communications. The proposed framework includes both large-scale and small-scale resource optimizations. The large-scale resource allocation is performed at the central base station based on large-scale channel information periodically collected from vehicles. On the other hand, the small-scale resource allocation is performed at the vehicles according to instantaneous channel and queuing information. We develop optimal solutions for both resource allocation problems. With the proposed optimal solutions, the latency performance at the occurrence of extreme events is enhanced by enabling spectrum sharing among the vehicles. Simulation results demonstrate that the proposed algorithm can effectively improve the URLLC performance compared against the benchmark algorithm.

In recent years, wirelessfederated learning(FL) has been proposed to support the mobile intelligent applications over the wireless network, which protects the data privacy and security by exchanging the parameter between mobile devices and thebase station(BS). However, the learning latency increases with the neural network scale due to the limited local computing power and communication bandwidth. To tackle this issue, we introduce model pruning for wireless FL to reduce the neural network scale. Device selection is also considered to further improve the learning performance. By removing the stragglers with low computing power or bad channel condition, the model aggregation loss caused by model pruning can be alleviated and the communication overhead can be effectively reduced. We analyze the convergence rate and learning latency of the proposed model pruning method and formulate an optimization problem to maximize the convergence rate under the given learning latency budget via jointly optimizing the pruning ratio, device selection, and wireless resource allocation. By solving the problem, the closed-form solutions of pruning ratio and wireless resource allocation are derived and the threshold-based device selection strategy is developed. Finally, extensive experiments are carried out to demonstrate that the proposed model pruning algorithm outperforms other existing schemes.

In this paper, a distributed power and spectrum allocation scheme is proposed to maximize the system energy efficiency (EE) for unlicensed device-to-device (D2D-U) networks. A non-convex optimization problem is formulated while considering the co-channel interference on licensed bands as the global constraint. To deal with the non-convex situation, the object function is converted into an equivalent convex one. Then, a distributed algorithm is developed to solve the optimization problem in which each D2D-U pair can find the optimal allocation strategy independently. The signaling overheads are analyzed and numerical results are presented to show that the proposed scheme is capable of achieving the optimal EE while confining the cochannel interference and guaranteeing the fair coexistence.

Unlike the conventional device-to-device (D2D) networks, the unlicensed D2D (D2D-U) pairs can not only reuse the licensed channels with the base station (BS) but also share the unlicensed channels with the WiFi stations. One challenge arises from the fact that the co-channel interference on licensed channels and the collision probability on unlicensed channels may cause extra power consumption at the terminals. Accordingly, we first propose a channel access method for the D2D-U pairs on unlicensed channels. Then, a decentralized joint spectrum and power allocation scheme is designed to minimize the power consumption at D2D-U pairs. Different from the existing distributed schemes, the proposed scheme can guarantee the global minimization of power consumption across the D2D-U pairs. Simulation results validate the theoretical analysis and verify the performance from the proposed scheme.

Many mission-critical and latency-sensitive applications require ultra-reliable and low-latency communications (URLLC), which has been listed as a new service category of 5G New Radio (NR). To guarantee stringent latency and reliability constraints, URLLC services always exclusively occupy the spectrum and have priority over enhanced mobile broadband (eMBB) communications in the current coexistence scenario, which will greatly affect the performance of eMBB services and degrade the utilization efficiency of the spectrum resource. On the other hand, millimeter-wave (mmWave) communications can fulfill the enormous throughput requirements of 5G cellular communications. In this paper, we introduce mmWave communications into URLLC systems to provide a more efficient coexistence for eMBB and URLLC. A novel mmWave URLLC system is first developed, where URLLC users are allowed to share the spectrum resources with eMBB users. Besides, multi-connectivity technology, which enables users to access multiple base stations simultaneously, is introduced to the mmWave URLLC system to enhance the reliability. Then, a resource management problem is formulated, which maximizes the throughput of eMBB users while guaranteeing the latency and reliability requirements of URLLC users. To obtain optimal solutions, we first divide it into three subproblems, i.e., power allocation, resource matching, and user paring, and then solve them respectively. Simulation results demonstrate the data rate improvement compared against the traditional coexistence scenario without reusing strategy. Moreover, the multi-connectivity functionality poses a great effect on guaranteeing the latency and reliability requirements for URLLC users.

The implementation of artificial intelligence (AI) in wireless networks is becoming more and more popular because of the growing number of mobile devices and the availability of huge amount of data. Directly transmitting data for centralized learning will cause long communication latency and may incur severe privacy issue as well. To address these issues, we consider the importance-aware federated edge learning (FEEL) system in this paper. Based on the relation between loss decay and gradient norm, a learning efficiency maximization problem is formulated by jointly considering the communication resource allocation and data selection. The closed-form results for optimal communication resource allocation and data selection are both developed, where some insights are also highlighted. Finally, the test results show that the proposed algorithm can effectively reduce the training latency and improve the learning accuracy as compared with some benchmark algorithms.

In wireless federated learning system, wireless communication and local computation have a significant impact on the learning latency due to the limited bandwidth and computing power of mobile devices. To reduce the learning latency, local stochastic gradient methods and gradient compression can be applied, which however would decrease the convergence rate. To tackle such issues, in this paper, the trade-off between the convergence rate and the learning latency is taken into account. We first formulate an optimization problem to maximize the convergence rate under the given training latency constraint via jointly optimizing the batchsize, compression ratio, and spectrum allocation. Then, by decomposing the problem into two subproblems, an adaptive algorithm is proposed to obtain the optimal solution. The results show that batchsize and compression ratio should be selected according to the computing power and channel state information of the devices to improve the convergence rate. Finally, experimental results are presented to verify the effectiveness of the proposed algorithm.

Deploying device-to-device (D2D) communication over underlaying cellular network can significantly enhance the spectrum utilization. However, co-channel interference will occur when D2D pairs share the same radio resource with cellular users. To mitigate the interference within a reasonable range, a machine learning based resource reuse scheme for D2D and cellular users is proposed in this paper. Specifically, we formulate an optimization problem to maximize the total throughput of D2D pairs and cellular users by optimally allocating subcarrier and power within the limits of the interference threshold. Since the formulated problem is a mixed integer non-linear programming problem, we solve it in two steps. First, we assign the orthogonal subcarriers to different cellular users to maximize the total throughput of all cellular users. Then, D2D pairs are allowed to reuse different subcarriers to further enhance the throughput without affecting the performance of cellular users. The second step is still NP-hard and therefore we propose a low-complexity algorithm based on the pointer network, a specific neural network structure proposed recently. Results reveal that, with remarkably reduced complexity, the proposed scheme outperforms the conventional resource allocation algorithms.

This paper investigates the user pairing in a full-duplex (FD) communication system, aiming at maximizing the overall data rate of the system by reducing inter-user interference. The traditional user pairing methods usually suffer from high computational complexity and therefore are not suitable for practical implementation. Inspired by the recent innovation of deep reinforcement learning (DRL), we develop a low-complexity algorithm for the user pairing problem in FD networks. We first transform the problem into a Markov decision process (MDP) to facilitate the implementation of DRL. We then utilize the semi-supervised training paradigm to speed up the training process by adding some expert experience to the replay buffer. Finally, our proposal is extensively tested via numerical simulation, which demonstrates that the DRL-based user pairing algorithm can achieve a good performance with a significantly reduced computational complexity.

In this paper, inspired by the minority game (MG), we propose a distributed user association mechanism for the heterogenous networks (HetNets) on unlicensed bands. Our proposal aims to achieve load balance under different resource contention schemes between the LTE-unlicensed (LTE-U) and Wi-Fi networks in a fully distributed fashion. To formulate the user association problem as MG, we first prove that there exists a unique cut-off value in the single-AP scenario for both listen-before-talk and duty cycle muting schemes. Meanwhile, both the pure strategy and the mixed strategy are developed and the Nash equilibria are achieved. We further extend our analysis into the scenario with multiple Wi-Fi access points and prove the existence and uniqueness of the cut-off value set. Numerical results show that the proposed MG-based user association algorithm can achieve load balance and fine spectrum utilization without channel state information (CSI). Some inspiring results are also highlighted through the numerical simulation. The proposed distributed mechanisms not only handle the LTE-U/Wi-Fi selection, but also give fascinating insights into user association and resource allocation in other scenarios of heterogenous networks.