Beam training and prediction in real-world millimeter-wave (mmWave) communications systems are challenging due to rapidly time-varying channels and strong interference from surrounding objects. In this context, widely available sensors, such as cameras and radars, can capture rich environmental information, enabling efficient beam management. This paper proposes a knowledge-distillation (KD)-enabled learning framework for developing lightweight and low-complexity models for beam prediction and tracking using real-world camera and radar data from the DeepSense 6G dataset. Specifically, a powerful teacher network based on convolutional neural networks (CNNs) and gated recurrent units (GRUs) is first designed to predict current and future beams from historical sensor observations. Then, a compact student model is constructed and trained via KD to transfer the predictive capability of the teacher model to a lightweight architecture. Simulation results demonstrate that jointly leveraging radar and image modalities significantly outperforms single-modality approaches. Moreover, the proposed student model achieves over 96

Reconfigurable antennas (RAs), capable of dynamically adapting their radiation patterns, polarization states, and operating frequencies, have emerged as a promising technology to meet the stringent performance requirements of sixth-generation (6G) wireless networks. This article systematically introduces essential hardware implementations of RAs and investigates advanced array architectures, such as fully-digital and tri-hybrid designs, emphasizing their capability to synergistically integrate electromagnetic (EM) reconfigurability with analog and digital signal processing. By facilitating coordinated beamforming across the EM and signal processing domains, RA arrays offer substantial flexibility and adaptability compared to conventional static antenna systems. Representative applications empowered by RA arrays, including integrated sensing and communication (ISAC), physical layer security (PLS), and near-field communications, are highlighted. A case study illustrates the effectiveness of RA arrays in optimizing beam steering, improving link robustness, and alleviating system power consumption. Finally, several open challenges and future research directions are outlined, emphasizing the need for advancements in theoretical modeling, hardware reliability, channel estimation techniques, intelligent optimization methods, and innovative network architectures, to fully realize the transformative impact of RAs in future 6G wireless networks.

This paper develops a comprehensive target modeling, beamforming optimization, and parameter estimation framework for extended-target sensing in wideband MIMO-OFDM integrated sensing and communication systems. We propose a parametric scattering model (PSM) that decouples target geometry from electromagnetic scattering characteristics, requiring only six nonlinear geometric parameters and linear radar cross-section (RCS) coefficients. Based on this compact structure, we derive a hybrid Bayesian Cramér-Rao bound (CRB) for joint estimation of azimuth, elevation, and range-related parameters. To handle inherent range ambiguities due to OFDM signaling, we analyze the range ambiguity function and introduce range sidelobe suppression constraints around the true range. Based on these constraints, we formulate an ambiguity-aware transmit beamforming design that minimizes a weighted geometric CRB subject to per-user signal-to-interference-plus-noise ratio (SINR) requirements and a total power budget. As benchmarks, we extend two other common models to the same wideband MIMO-OFDM scenario. We also derive maximum a posteriori estimators and a computational complexity analysis for all three models. Simulation results demonstrate that the proposed PSM-based approach achieves improved target localization with significantly reduced runtime for beamforming optimization and parameter estimation, while consistently satisfying communication SINR requirements.

Integrated sensing and communication (ISAC) has emerged as a key feature for sixth-generation (6G) networks, providing an opportunity to meet the dual demands of communication and sensing. Existing ISAC research primarily focuses on baseband optimization at individual access points, with limited attention to the roles of electromagnetic (EM) shaping and network-wide coordination. The intricate interdependencies between these domains remain insufficiently explored, leaving their full potential for enhancing ISAC performance largely untapped. To bridge this gap, we consider multi-domain ISAC optimization integrating EM shaping, baseband processing, and network cooperation strategies that facilitate efficient resource management and system-level design. We analyze the fundamental trade-offs between these domains and offer insights into domain-specific and cross-domain strategies contributing to ISAC performance and efficiency. We then conduct a case study demonstrating the effectiveness of joint multi-domain optimization. Finally, we discuss key challenges and future research directions to connect theoretical advancements and practical ISAC deployments. This work paves the way for intelligent and scalable ISAC architectures, providing critical insights for their seamless integration into next-generation wireless networks.

Integrated sensing and communication (ISAC) can substantially improve spectral, hardware, and energy efficiency by unifying radar sensing and data communications. In wideband and scattering-rich environments, clutter often dominates weak target reflections and becomes a fundamental bottleneck for reliable sensing. Practical ISAC clutter includes "cold" clutter arising from environmental backscatter of the probing waveform and "hot" clutter induced by external interference and reflections from the environment whose statistics can vary rapidly over time. In this article, we develop a unified wideband multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) signal model that captures both clutter types across the space, time, and frequency domains. Building on this model, we review clutter characterization at multiple levels, including amplitude statistics, robust spherically invariant random vector (SIRV) modeling, and structured covariance representations suitable for limited-snapshot regimes. We then summarize receiver-side suppression methods in the temporal and spatial domains, together with extensions to space-time adaptive processing (STAP) and space-frequency-time adaptive processing (SFTAP), and we provide guidance on selecting techniques under different waveform and interference conditions. To move beyond reactive suppression, we discuss clutter-aware transceiver co-design that couples beamforming and waveform optimization with practical communication quality-of-service (QoS) constraints to enable proactive clutter avoidance. We conclude with open challenges and research directions toward environment-adaptive and clutter-resilient ISAC for the next-generation networks.

Integrated sensing and communications (ISAC) has emerged as a promising paradigm to unify wireless communications and radar sensing, enabling efficient spectrum and hardware utilization. A core challenge with realizing the gains of ISAC stems from the unique challenges of dual purpose beamforming design due to the highly non-convex nature of key performance metrics such as sum rate for communications and the Cramer-Rao lower bound (CRLB) for sensing. In this paper, we propose a low-complexity structured approach to ISAC beamforming optimization to simultaneously enhance spectral efficiency and estimation accuracy. Specifically, we develop a successive convex approximation (SCA) based algorithm which transforms the original non-convex problem into a sequence of convex subproblems ensuring convergence to a locally optimal solution. Furthermore, leveraging the proposed SCA framework and the Lagrange duality, we derive the optimal beamforming structure for CRLB optimization in ISAC systems. Our findings characterize the reduction in radar streams one can employ without affecting performance. This enables a dimensionality reduction that enhances computational efficiency. Numerical simulations validate that our approach achieves comparable or superior performance to the considered benchmarks while requiring much lower computational costs.

Symbol-level precoding (SLP) can achieve remarkable gains in multi-user multiple-input-single-output (MU-MISO) systems, while its extension to multi-user multiple-input-multiple-output (MU-MIMO) systems offers even greater potential by exploiting the spatial dimensions at both the transmitter and receiver. However, existing MU-MIMO SLP designs require symbol-dependent receive combining matrices or rely on alternating iterative optimization, resulting in high signaling overhead and complexity. To overcome these limitations, this paper revisits the receiver design for SLP-based MU-MIMO systems from a minimum mean square error (MMSE) perspective. By explicitly exploiting the rank-one structure of the effective channel induced by SLP, it is proven that the MMSE-optimal linear receiver admits a simple matched-filter form with low computational complexity. Furthermore, it is analytically demonstrated that the conventional regularized MMSE (RMMSE) receiver yields identical decoding performance for any choice of the regularization factor under SLP transmission. Simulation results validate the theoretical analysis and demonstrate that the proposed receiver structures achieve superior performance with substantially reduced complexity compared to existing approaches.

In this paper, we investigate channel estimation for reconfigurable intelligent surface (RIS) empowered millimeter-wave (mmWave) multi-user single-input multiple-output communication systems using low-resolution quantization. Due to the high cost and power consumption of analog-to-digital converters (ADCs) in large antenna arrays and for wide signal bandwidths, designing mmWave systems with low-resolution ADCs is beneficial. To tackle this issue, we propose a channel estimation design using task-based quantization that considers the underlying hybrid analog and digital architecture in order to improve the system performance under finite bit-resolution constraints. Our goal is to accomplish a channel estimation task that minimizes the mean squared error distortion between the true and estimated channel. We develop two types of channel estimators: a cascaded channel estimator for an RIS with purely passive elements, and an estimator for the separate RIS-related channels that leverages additional information from a few semi-passive elements at the RIS capable of processing the received signals with radio frequency chains. Numerical results demonstrate that the proposed channel estimation designs exploiting task-based quantization outperform purely digital methods and can effectively approach the performance of a system with unlimited resolution ADCs. Furthermore, the proposed channel estimators are shown to be superior to baselines with small training overhead.

Sensing-aided beam tracking is a promising approach to reduce the overhead for millimeter-wave beam management. However, real-world application remains challenging due to rapid channel variations and substantial environmental differences across deployment scenarios. Developing low-complexity sensing assisted approaches that generalize to diverse environments can alleviate the problem. With this motivation, this paper proposes a lightweight vision-aided model for cross-environment beam tracking. The task is formulated as a sequence-to-sequence classification problem, where the model jointly predicts the current and future optimal beams from past visual observations. We develop a low-complexity model based on depthwise separable convolutions and introduce hierarchical data augmentation and beam power-based label smoothing to improve robustness and generalization. Experimental results on real-world images from two geometrically distinct DeepSense 6G scenarios show that the proposed strategies consistently improve cross-environment beam prediction accuracy up to 84

Recent advancements in millimeter-wave (mmWave) radar technology have made it possible for radars to generate image-like observations, a capability that was previously challenging to achieve. These radar-generated images can be 4-D (azimuth and elevation angles + range + Doppler) if the sensor offers sufficiently fine spatial resolution. Angular resolution is the system’s ability to distinguish between objects that are in close angular proximity, while range discrimination is achieved through the large bandwidth supported by mmWave frequencies. By employing a substantial number of antenna elements, mmWave radars can perform beamforming in both transmit and receive directions, reducing interference and significantly improving spatial resolution. This allows the sensor to capture detailed information about an object’s distance, velocity, and 2-D angular position. Such capabilities are critical for applications like autonomous driving (AD), in-car monitoring, industrial automation, medical imaging, and security surveillance. This article explores emerging 4-D multiple-input–multiple-output (MIMO) imaging radar technology, highlighting its potential for cost-efficient, high-resolution image-like radar observations. It examines available sensors, their design methodologies, sensing robustness, and gaps in the current application of MIMO radar. In addition, the realization of massive MIMO radars through sparse and virtual array configurations is explored in this work. This study also considers potential new features and advancements in the field. Key topics include signal processing and array configuration design, both essential for optimizing radar performance. In addition, this article addresses various challenges and showcases ongoing industry efforts driving innovation in 4-D MIMO imaging radar systems.

The constructive interference (CI)-based block-level precoding (CI-BLP) approach reduces computational complexity compared to conventional CI-based symbol-level precoding (CI-SLP) and provides additional design flexibility due to its relaxed block-level design. However, using a constant precoding matrix within each block limits the system’s degrees of freedom (DoFs), resulting in significant performance degradation for large block lengths. To overcome this limitation, we propose using a reconfigurable intelligent surface (RIS) to enhance the propagation environment and offer extra DoFs. We jointly optimize the BLP matrix and the block-level RIS scattering matrix for active RIS and passive beyond-diagonal RIS (BD-RIS) aided communication systems using an alternating optimization (AO) algorithm. The BLP subproblem admits a closed-form solution and can be reformulated as a quadratic programming (QP) problem. For active RIS, two architectures are considered: uniform-amplitude and adaptive-amplitude, where the scattering subproblems are approximated as convex, and two different projection methods are employed to ensure feasibility. Furthermore, to reduce power consumption and increase design flexibility, we formulate a block-level passive BD-RIS scattering optimization subproblem, which is solved using an alternating direction method of multipliers (ADMM) algorithm. Simulation results demonstrate that RIS-aided CI-BLP designs significantly outperform conventional approaches without RIS. In particular, BD-RIS achieves higher CI gains than active RIS, benefiting from more available design flexibility, albeit at the cost of increased computational complexity.

Polarization diversity offers a cost- and space-efficient solution to enhance the performance of integrated sensing and communication systems. Polarimetric sensing exploits the signal's polarity to extract details about the target such as shape, pose, and material composition. From a communication perspective, polarization diversity can enhance the reliability and throughput of communication channels. This paper proposes an integrated polarimetric sensing and communication (IPSAC) system that jointly conducts polarimetric sensing and communications. We study the use of single-port polarization-reconfigurable antennas to adapt to channel depolarization effects, without the need for separate RF chains for each polarization. We address the problem of optimizing waveforms and polarizations based on two sensing metrics. We first consider minimizing the mean square error (MSE) of the target depolarization parameter estimate, which is a critical task for various polarimetric radar applications such as rainfall forecasting, vegetation identification, and target classification. To address this nonconvex problem, we apply semi-definite relaxation (SDR) and majorization-minimization (MM) optimization techniques. Next, we consider a design that maximizes the target signal-to-interference-plus-noise ratio (SINR) leveraging prior knowledge of the target and clutter depolarization statistics to enhance the target detection performance. To tackle this problem, we modify the solution developed for MSE minimization subject to the same quality-of-service (QoS) constraints. Extensive simulations show that the proposed polarization reconfiguration method substantially improves the depolarization parameter MSE. Furthermore, the proposed method considerably boosts the target SINR due to polarization diversity, particularly in cluttered environments.

Non-orthogonal multiple access (NOMA) is a promising technology for next-generation wireless communication systems due to its enhanced spectral efficiency. However, wireless communication is facing increasing requirements for security. To that end, jamming mitigation using multi-antennas has emerged as an important research topic. In this paper, we consider an uplink NOMA system with a reconfigurable intelligent surface (RIS) that assists the uplink users and, at the same time, mitigates the jammer. Our goal is to minimize the total users' transmitted power under signal-to-interference-plus-noise ratio constraints at the base station. To be effective, typically a high-dimensional RIS is needed, leading to a large optimization problem, which in general faces convergence problems. We propose an iterative algorithm for this high-dimensional non-convex optimization problem that converges with a jammer comprising as many as 64 antennas, and an RIS with 128 elements. More specifically, we introduce a design and optimize the performance of an absorptive RIS (A-RIS). Compared to a standard RIS, we show that an A-RIS can dramatically reduce the users' required transmit power and successfully mitigate the jammer. The A-RIS is in particular useful in cases when the number of jammer antennas is of the same order as the number of A-RIS elements.

Reconfigurable Intelligent Surfaces (RISs) enhance wireless communication by steering electromagnetic waves through tunable reflection elements. However, scaling conventional RIS architectures to large arrays introduces significant wiring and control complexity. To address this, we investigate a wave-controlled RIS that uses biasing transmission lines carrying biasing standing waves (BSWs), which are sampled at each element to generate control voltages. We propose a sample-and-hold (S/H) circuit for precise temporal voltage acquisition and evaluate its performance in scenarios where neither channel state information (CSI) nor mathematical RIS models are available. Instead, optimization is fully data-driven: received power measurements are used to train a neural network (NN) that estimates the radiation pattern. A Genetic Algorithm (GA) refines the NN architecture, while Simulated Annealing (SA) tunes the BSW amplitudes to maximize a signal-to-leakage-plus-noise ratio (SLNR) metric using NN-based feedback. Optimized configurations are stored in a lookup table for real-time RIS control. We assess performance across diverse propagation conditions – including multipath and non-line-of-sight (NLoS) channels – under varying dataset sizes and SLNR targets. Relative to envelope-detector-based sampling, the proposed S/H circuit yields more accurate radiation pattern control and SLNR performance approaching that of an ideal system with perfect CSI and exact models. This idealized baseline further confirms that the S/H-based wave-controlled RIS can effectively optimize SLNR even in NLoS-dominated channels such as Rayleigh fading.

This work studies near-field secure communications through transmit beamfocusing. We examine the benefit of having a protected eavesdropper-free zone around the legitimate receiver, and we determine the worst-case secrecy performance against a potential eavesdropper located anywhere outside the protected zone. A max-min optimization problem is formulated for the beamfocusing design with and without artificial noise transmission. Despite the NP-hardness of the problem, we develop a synchronous gradient descent-ascent framework that approximates the global maximin solution. A low-complexity solution is also derived that delivers excellent performance over a wide range of operating conditions. We further extend this study to a scenario where it is not possible to physically enforce a protected zone. To this end, we consider secure communications through the creation of a virtual protected zone using a full-duplex legitimate receiver. Numerical results demonstrate that exploiting either the physical or virtual receiver-centered protected zone with appropriately designed beamfocusing is an effective strategy for achieving secure near-field communications.

Extremely large-scale antenna arrays (XL-arrays) and ultra-high frequencies are two fundamental technologies for future sixth-generation (6G) wireless networks, providing enhanced system capacity and substantial bandwidth expansion. To fully leverage these technological advancements, conventional far-field models must be replaced by more accurate near-field spherical-wave propagation models. This paper investigates a near-field communication system comprising a hybrid analog-digital beamforming base station (BS) and multiple mobile users, aiming to maximize system sum-rate through optimized codebook design, beam selection, and digital precoding. To accommodate dynamic user distributions, we propose two model-agnostic meta-learning (MAML)-based frameworks that enable prompt adaptation by learning well-initialized models for fine tuning. The first framework integrates the MAML method with a deep neural network (DNN) to design near-field codebooks tailored to the user distributions, addressing the limitations of conventional uniform codebooks. The second framework employs a joint neural network (NN) for beam selection and digital precoding, combining deep reinforcement learning (DRL) and deep unfolding. The DRL NN formulates beam selection as a Markov Decision Process, while the deep-unfolding NN approximates optimal digital precoding through a lightweight iterative algorithm without matrix inversion. Simulation results show that the proposed frameworks significantly outperform conventional methods, achieving superior generalization and overall performance in dynamic near-field scenarios.

Integrated Sensing and Communication (ISAC) is a key emerging 6G technology. Despite progress, ISAC still lacks scalable methods for joint AP clustering and user/target scheduling in distributed deployments under fronthaul limits. Moreover, existing ISAC solutions largely rely on centralized processing and full channel state information, limiting scalability. This paper addresses joint access point (AP) clustering, user and target scheduling, and AP mode selection in distributed cell-free ISAC systems operating with constrained fronthaul capacity. We formulate the problem as a mixed-integer linear program (MILP) that jointly captures interference coupling, RF-chain limits, and sensing requirements, providing optimal but computationally demanding solutions. To enable real-time and scalable operation, we propose ASSENT (ASSociation and ENTity selection), a graph neural network (GNN) framework trained on MILP solutions to efficiently learn association and mode-selection policies directly from lightweight link statistics. Simulations show that ASSENT achieves near-optimal utility while accurately learning the underlying associations. Additionally, its single forward pass inference reduces decision latency compared to optimization-based methods. An open-source Python/PyTorch implementation with full datasets is provided to facilitate reproducible and extensible research in cell-free ISAC.

Infrastructure-mounted sensors can capture rich environmental information to enhance communications and facilitate beamforming in millimeter-wave systems. This work presents an efficient sensing-assisted long-term beam tracking framework that selects optimal beams from a codebook for current and multiple future time slots. We first design a large attention-enhanced neural network (NN) to fully exploit past visual observations for beam tracking. A convolutional NN extracts compact image features, while gated recurrent units with attention capture the temporal dependencies within sequences. The large NN then acts as the teacher to guide the training of a lightweight student NN via knowledge distillation. The student requires shorter input sequences yet preserves long-term beam prediction ability. Numerical results demonstrate that the teacher achieves Top-5 accuracies exceeding 93

This paper focuses on precoding design in multi-antenna systems with improper Gaussian interference (IGI), characterized by correlated real and imaginary parts. We first study block level precoding (BLP) and symbol level precoding (SLP) assuming the receivers apply a pre-whitening filter to decorrelate and normalize the IGI. We then shift to the scenario where the base station (BS) incorporates the IGI statistics in the SLP design, which allows the receivers to employ a standard detection algorithm without pre-whitenting. Finally we address the case where the channel and statistics of the IGI are unknown, and we formulate robust BLP and SLP designs that minimize the worst case performance in such settings. Interestingly, we show that for BLP, the worst-case IGI is in fact proper, while for SLP the worst case occurs when the interference signal is maximally improper, with fully correlated real and imaginary parts. Numerical results reveal the superior performance of SLP in terms of symbol error rate (SER) and energy efficiency (EE), especially for the case where there is uncertainty in the non-circularity of the jammer.

Symbol-level precoding (SLP) is a promising solution for addressing the inherent interference problem in dual-functional radar-communication (DFRC) signal designs. This paper considers an SLP-DFRC signal design problem which optimizes the radar performance under communication performance constraints. We show that a common phase modulation applied to the transmit signals from an antenna array does not affect the performance of different radar sensing metrics, including beampattern similarity, signal-to-interference-plus-noise ratio (SINR), and Cramér-Rao lower bound (CRLB). We refer to this as symmetric-rotation invariance, upon which we develop low-complexity yet efficient DFRC signal design algorithms. More specifically, we propose a symmetric non-convexity (SNC)-based DFRC algorithm that relies on the non-convexity of the radar sensing metrics to identify a set of radar-only solutions. Based on these solutions, we further exploit the symmetry property of the radar sensing metrics to efficiently design the DFRC signal. We show that the proposed SNC-based algorithm is versatile in the sense that it can be applied to the DFRC signal optimization of all three sensing metrics mentioned above (beampattern, SINR, and CRLB). In addition, since the radar sensing metrics are independent of the communication channel and data symbols, the set of radar-only solutions can be constructed offline, thereby reducing the computational complexity. We also develop an accelerated SNC-based algorithm that further reduces the complexity. Finally, we numerically demonstrate the superiority of the proposed algorithms compared to existing methods in terms of sensing and communication performance as well as computational requirements.