Compressed BC-LISTA via Low-Rank Convolutional Decomposition

We study Sparse Signal Recovery (SSR) methods for multichannel imaging with compressed {forward and backward} operators that preserve reconstruction accuracy. We propose a Compressed Block-Convolutional (C-BC) measurement model based on a low-rank Convolutional Neural Network (CNN) decomposition that is analytically initialized from a low-rank factorization of physics-derived forward/backward operators in time delay-based measurements. We use Orthogonal Matching Pursuit (OMP) to select a compact set of basis filters from the analytic model and compute linear mixing coefficients to approximate the full model. We consider the Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) network as a representative example for which the C-BC-LISTA extension is presented. In simulated multichannel ultrasound imaging across multiple Signal-to-Noise Ratios (SNRs), C-BC-LISTA requires substantially fewer parameters and smaller model size than other state-of-the-art (SOTA) methods while improving reconstruction accuracy. In ablations over OMP, Singular Value Decomposition (SVD)-based, and random initializations, OMP-initialized structured compression performs best, yielding the most efficient training and the best performance.

SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in numerous applications, its theoretical underpinnings remain only partially understood. In this work, we adopt a Bayesian perspective on KD to rigorously analyze the convergence behavior of students trained with Stochastic Gradient Descent (SGD). We study two regimes: $(i)$ when the teacher provides the exact Bayes Class Probabilities (BCPs); and $(ii)$ supervision with noisy approximations of the BCPs. Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision. We further characterize how the level of noise affects generalization and accuracy. Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD. Consistent with our analysis, we experimentally demonstrate that students distilled from Bayesian teachers not only achieve higher accuracies (up to +4.27%), but also exhibit more stable convergence (up to 30% less noise), compared to students distilled from deterministic teachers.

Ultra-Massive MIMO with Orthogonal Chirp Division Multiplexing for Near-Field Sensing and Communication Integration

This paper integrates the emerging ultra-massive multiple-input multiple-output (UM-MIMO) technique with orthogonal chirp division multiplexing (OCDM) waveform to tackle the challenging near-field integrated sensing and communication (ISAC) problem. Specifically, we conceive a comprehensive ISAC architecture, where an UM-MIMO base station adopts OCDM waveform for communications and a co-located sensing receiver adopts the frequency-modulated continuous wave (FMCW) detection principle to simplify the associated hardware. For sensing tasks, several OCDM subcarriers, namely, dedicated sensing subcarriers (DSSs), are each transmitted through a dedicated sensing antenna (DSA) within the transmit antenna array. By judiciously designing the DSS selection scheme and optimizing receiver parameters, the FMCW-based sensing receiver can decouple the echo signals from different DSAs with significantly reduced hardware complexity. This setup enables the estimation of ranges and velocities of near-field targets in an antenna-pairwise manner. Moreover, by leveraging the spatial diversity of UM-MIMO, we introduce the concept of virtual bistatic sensing (VIBS), which incorporates the estimates from multiple antenna pairs to achieve high-accuracy target positioning and three-dimensional velocity measurement. The VIBS paradigm is immune to hostile channel environments characterized by spatial non-stationarity and uncorrelated multipath environment. Furthermore, the channel estimation of UM-MIMO OCDM systems enhanced by the sensing results is investigated. Simulation results demonstrate that the proposed ISAC scheme enhances sensing accuracy, and also benefits communication performance.

pDANSE: Particle-based Data-driven Nonlinear State Estimation from Nonlinear Measurements

We consider the problem of designing a data-driven nonlinear state estimation (DANSE) method that uses (noisy) nonlinear measurements of a process whose underlying state transition model (STM) is unknown. Such a process is referred to as a model-free process. A recurrent neural network (RNN) provides parameters of a Gaussian prior that characterize the state of the model-free process, using all previous measurements at a given time point. In the case of DANSE, the measurement system was linear, leading to a closed-form solution for the state posterior. However, the presence of a nonlinear measurement system renders a closed-form solution infeasible. Instead, the second-order statistics of the state posterior are computed using the nonlinear measurements observed at the time point. We address the nonlinear measurements using a reparameterization trick-based particle sampling approach, and estimate the second-order statistics of the state posterior. The proposed method is referred to as particle-based DANSE (pDANSE). The RNN of pDANSE uses sequential measurements efficiently and avoids the use of computationally intensive sequential Monte-Carlo (SMC) and/or ancestral sampling. We describe the semi-supervised learning method for pDANSE, which transitions to unsupervised learning in the absence of labeled data. Using a stochastic Lorenz-$63$ system as a benchmark process, we experimentally demonstrate the state estimation performance for four nonlinear measurement systems. We explore cubic nonlinearity and a camera-model nonlinearity where unsupervised learning is used; then we explore half-wave rectification nonlinearity and Cartesian-to-spherical nonlinearity where semi-supervised learning is used. The performance of state estimation is shown to be competitive vis-\`a-vis particle filters that have complete knowledge of the STM of the Lorenz-$63$ system.

Bayesian Signal Separation via Plug-and-Play Diffusion-Within-Gibbs Sampling

We propose a posterior sampling algorithm for the problem of estimating multiple independent source signals from their noisy superposition. The proposed algorithm is a combination of Gibbs sampling method and plug-and-play (PnP) diffusion priors. Unlike most existing diffusion-model-based approaches for signal separation, our method allows source priors to be learned separately and flexibly combined without retraining. Moreover, under the assumption of perfect diffusion model training, the proposed method provably produces samples from the posterior distribution. Experiments on the task of heartbeat extraction from mixtures with synthetic motion artifacts demonstrate the superior performance of our method over existing approaches.

RIS-Assisted Near-Field ISAC for Multi-Target Indication in NLoS Scenarios

Enabling multi-target sensing in near-field integrated sensing and communication (ISAC) systems is a key challenge, particularly when line-of-sight paths are blocked. This paper proposes a beamforming framework that leverages a reconfigurable intelligent surface (RIS) to achieve multi-target indication. Our contribution is the extension of classic beampattern gain and inter-target cross-correlation metrics to the near-field, leveraging both angle and distance information to discriminate between multiple users and targets. We formulate a problem to maximize the worst-case sensing performance by jointly designing the beamforming at the base station and the phase shifts at the RIS, while guaranteeing communication rates. The non-convex problem is solved via an efficient alternating optimization (AO) algorithm that utilizes semidefinite relaxation (SDR). Simulations demonstrate that our RIS-assisted framework enables high-resolution sensing of co-angle targets in blocked scenarios.

Plug-and-Play Latent Diffusion for Electromagnetic Inverse Scattering with Application to Brain Imaging

Electromagnetic (EM) imaging is an important tool for non-invasive sensing with low-cost and portable devices. One emerging application is EM stroke imaging, which enables early diagnosis and continuous monitoring of brain strokes. Quantitative imaging is achieved by solving an inverse scattering problem (ISP) that reconstructs permittivity and conductivity maps from measurements. In general, the reconstruction accuracy is limited by its inherent nonlinearity and ill-posedness. Existing methods, including learning-free and learning-based approaches, fail to either incorporate complicated prior distributions or provide theoretical guarantees, posing difficulties in balancing interpretability, distortion error, and reliability. To overcome these limitations, we propose a posterior sampling method based on latent diffusion for quantitative EM brain imaging, adapted from a generative plug-and-play (PnP) posterior sampling framework. Our approach allows to flexibly integrate prior knowledge into physics-based inversion without requiring paired measurement-label datasets. We first learn the prior distribution of targets from an unlabeled dataset, and then incorporate the learned prior into posterior sampling. In particular, we train a latent diffusion model on permittivity and conductivity maps to capture their prior distribution. Then, given measurements and the forward model describing EM wave physics, we perform posterior sampling by alternating between two samplers that respectively enforce the likelihood and prior distributions. Finally, reliable reconstruction is obtained through minimum mean squared error (MMSE) estimation based on the samples. Experimental results on brain imaging demonstrate that our approach achieves state-of-the-art performance in reconstruction accuracy and structural similarity while maintaining high measurement fidelity.

Derivative-Free Optimization-Empowered Wireless Channel Reconfiguration for 6G

Reconfigurable antennas, including reconfigurable intelligent surface (RIS), movable antenna (MA), fluid antenna (FA), and other advanced antenna techniques, have been studied extensively in the context of reshaping wireless propagation environments for 6G and beyond wireless communications. Nevertheless, how to reconfigure/optimize the real-time controllable coefficients to achieve a favorable end-to-end wireless channel remains a substantial challenge, as it usually requires accurate modeling of the complex interaction between the reconfigurable devices and the electromagnetic waves, as well as knowledge of implicit channel propagation parameters. In this paper, we introduce a derivative-free optimization (a.k.a., zeroth-order (ZO) optimization) technique to directly optimize reconfigurable coefficients to shape the wireless end-to-end channel, without the need of channel modeling and estimation of the implicit environmental propagation parameters. We present the fundamental principles of ZO optimization and discuss its potential advantages in wireless channel reconfiguration. Two case studies for RIS and movable antenna-enabled single-input single-output (SISO) systems are provided to show the superiority of ZO-based methods as compared to state-of-the-art techniques. Finally, we outline promising future research directions and offer concluding insights on derivative-free optimization for reconfigurable antenna technologies.

An Integrated Sensing and Communication System for Time-Sensitive Targets with Random Arrivals

In 6G networks, integrated sensing and communication (ISAC) is envisioned as a key technology that enables wireless systems to perform joint sensing and communication using shared hardware, antennas and spectrum. ISAC designs facilitate emerging applications such as smart cities and autonomous driving. Such applications also demand ultra-reliable and low-latency communication (URLLC). Thus, an ISAC-enabled URLLC system can prioritize time-sensitive targets and ensure information delivery under strict latency and reliability constraints. We propose a bi-static MIMO ISAC system to detect the arrival of URLLC messages and prioritize their delivery. In this system, a base station (BS) communicates with a user equipment (UE) and a sensing receiver (SR) is deployed to collect echo signals reflected from a target of interest. The BS regularly transmits messages of enhanced mobile broadband (eMBB) services to the UE. During each eMBB transmission, if the SR senses the presence of a target of interest, it immediately triggers the transmission of an additional URLLC message. To reinforce URLLC transmissions, we propose a dirty-paper coding (DPC)-based technique that mitigates the interference of both eMBB and sensing signals. To decode the eMBB message, we consider two approaches for handling the URLLC interference: treating interference as noise and successive interference cancellation. For this system, we formulate the rate-reliability-detection trade-off in the finite blocklength (FBL) regime by evaluating the communication rate of the eMBB transmissions, the reliability of the URLLC transmissions and the probability of the target detection. Our numerical analysis show that our proposed DPC-based ISAC scheme significantly outperforms power-sharing and traditional time-sharing schemes. In particular, it achieves higher eMBB transmission rate while satisfying both URLLC and sensing constraints.

EOTNet: Deep Memory Aided Bayesian Filter for Extended Object Tracking

Extended object tracking methods based on random matrices, founded on Bayesian filters, have been able to achieve efficient recursive processes while jointly estimating the kinematic states and extension of the targets. Existing random matrix approaches typically assume that the evolution of state and extension follows a first-order Markov process, where the current estimate of the target depends solely on the previous moment. However, in real-world scenarios, this assumption fails because the evolution of states and extension is usually non-Markovian. In this paper, we introduce a novel extended object tracking method: a Bayesian recursive neural network assisted by deep memory. Initially, we propose an equivalent model under a non-Markovian assumption and derive the implementation of its Bayesian filtering framework. Thereafter, Gaussian approximation and moment matching are employed to derive the analytical solution for the proposed Bayesian filtering framework. Finally, based on the closed-form solution, we design an end-to-end trainable Bayesian recursive neural network for extended object tracking. Experiment results on simulated and real-world datasets show that the proposed methods outperforms traditional extended object tracking methods and state-of-the-art deep learning approaches.