Knowledge Distillation for mmWave Beam Prediction Using Sub-6 GHz Channels

Beamforming in millimeter-wave (mmWave) high-mobility environments typically incurs substantial training overhead. While prior studies suggest that sub-6 GHz channels can be exploited to predict optimal mmWave beams, existing methods depend on large deep learning (DL) models with prohibitive computational and memory requirements. In this paper, we propose a computationally efficient framework for sub-6 GHz channel-mmWave beam mapping based on the knowledge distillation (KD) technique. We develop two compact student DL architectures based on individual and relational distillation strategies, which retain only a few hidden layers yet closely mimic the performance of large teacher DL models. Extensive simulations demonstrate that the proposed student models achieve the teacher's beam prediction accuracy and spectral efficiency while reducing trainable parameters and computational complexity by 99%.

Generative Decompression: Optimal Lossy Decoding Against Distribution Mismatch

This paper addresses optimal decoding strategies in lossy compression where the assumed distribution for compressor design mismatches the actual (true) distribution of the source. This problem has immediate relevance in standardized communication systems where the decoder acquires side information or priors about the true distribution that are unavailable to the fixed encoder. We formally define the mismatched quantization problem, demonstrating that the optimal reconstruction rule, termed generative decompression, aligns with classical Bayesian estimation by taking the conditional expectation under the true distribution given the quantization indices and adapting it to fixed-encoder constraints. This strategy effectively performs a generative Bayesian correction on the decoder side, strictly outperforming the conventional centroid rule. We extend this framework to transmission over noisy channels, deriving a robust soft-decoding rule that quantifies the inefficiency of standard modular source--channel separation architectures under mismatch. Furthermore, we generalize the approach to task-oriented decoding, showing that the optimal strategy shifts from conditional mean estimation to maximum a posteriori (MAP) detection. Experimental results on Gaussian sources and deep-learning-based semantic classification demonstrate that generative decompression closes a vast majority of the performance gap to the ideal joint-optimization benchmark, enabling adaptive, high-fidelity reconstruction without modifying the encoder.

LWM-Spectro: A Foundation Model for Wireless Baseband Signal Spectrograms

The received in-phase and quadrature (I/Q) baseband signals inherently encode physical-layer and channel characteristics of wireless links. Learning robust and transferable representations directly from such raw signals, however, remains challenging due to heterogeneous communication systems, diverse propagation environments, and limited labeled data. To address this, we present LWM-Spectro, a transformer-based foundation model pretrained on large-scale I/Q data represented as time-frequency spectrograms. The model leverages self-supervised masked modeling, contrastive learning, and a mixture-of-experts (MoE) architecture to learn general-purpose wireless representations. These representations transfer effectively to downstream tasks such as modulation classification and joint SNR/mobility recognition, even with minimal supervision. Across tasks, LWM-Spectro consistently outperforms state-of-the-art deep learning baselines in both few-shot and data-rich regimes, providing a unified foundation for wireless learning.

Wireless Dataset Similarity: Measuring Distances in Supervised and Unsupervised Machine Learning

This paper introduces a task- and model-aware framework for measuring similarity between wireless datasets, enabling applications such as dataset selection/augmentation, simulation-to-real (sim2real) comparison, task-specific synthetic data generation, and informing decisions on model training/adaptation to new deployments. We evaluate candidate dataset distance metrics by how well they predict cross-dataset transferability: if two datasets have a small distance, a model trained on one should perform well on the other. We apply the framework on an unsupervised task, channel state information (CSI) compression, using autoencoders. Using metrics based on UMAP embeddings, combined with Wasserstein and Euclidean distances, we achieve Pearson correlations exceeding 0.85 between dataset distances and train-on-one/test-on-another task performance. We also apply the framework to a supervised beam prediction in the downlink using convolutional neural networks. For this task, we derive a label-aware distance by integrating supervised UMAP and penalties for dataset imbalance. Across both tasks, the resulting distances outperform traditional baselines and consistently exhibit stronger correlations with model transferability, supporting task-relevant comparisons between wireless datasets.

Comparing Stochastic and Ray-tracing Datasets in Machine Learning for Wireless Applications

Machine learning for wireless systems is commonly studied using standardized stochastic channel models (e.g., TDL/CDL/UMa) because of their legacy in wireless communication standardization and their ability to generate data at scale. However, some of their structural assumptions may diverge from real-world propagation. This paper asks when these models are sufficient and when ray-traced (RT) data - a proxy for the real world - provides tangible benefits. To answer these questions, we conduct an empirical study on two representative tasks: CSI compression and temporal channel prediction. Models are trained and evaluated using in-domain, cross-domain, and small-data fine-tuning protocols. Across settings, we observe that stochastic-only evaluation may over- or under-estimate performance relative to RT. These findings support a task-aware recipe where stochastic models can be leveraged for scalable pre-training and for tasks that do not rely on strong spatiotemporal coupling. When that coupling matters, pre-training and evaluation should be grounded in spatially consistent or geometrically similar RT scenarios. This study provides initial guidance to inform future discussions on benchmarking and standardization.

Generative Decoding of Compressed CSI for MIMO Precoding Design

Massive MIMO systems can enhance spectral and energy efficiency, but they require accurate channel state information (CSI), which becomes costly as the number of antennas increases. While machine learning (ML) autoencoders show promise for CSI reconstruction and reducing feedback overhead, they introduce new challenges with standardization, interoperability, and backward compatibility. Also, the significant data collection needed for training makes real-world deployment difficult. To overcome these drawbacks, we propose an ML-based, decoder-only solution for compressed CSI. Our approach uses a standardized encoder for CSI compression on the user side and a site-specific generative decoder at the base station to refine the compressed CSI using environmental knowledge. We introduce two training schemes for the generative decoder: An end-to-end method and a two-stage method, both utilizing a goal-oriented loss function. Furthermore, we reduce the data collection overhead by using a site-specific digital twin to generate synthetic CSI data for training. Our simulations highlight the effectiveness of this solution across various feedback overhead regimes.

Constrained Multimodal Sensing-Aided Communications: A Dynamic Beamforming Design

Using multimodal sensory data can enhance communications systems by reducing the overhead and latency in beam training. However, processing such data incurs high computational complexity, and continuous sensing results in significant power and bandwidth consumption. This gives rise to a tradeoff between the (multimodal) sensing data acquisition rate and communications performance. In this work, we develop a constrained multimodal sensing-aided communications framework where dynamic sensing and beamforming are performed under a sensing budget. Specifically, we formulate an optimization problem that maximizes the average received signal-to-noise ratio (SNR) of user equipment, subject to constraints on the average number of sensing actions and power budget. Using the Saleh-Valenzuela mmWave channel model, we construct the channel primarily based on position information obtained via multimodal sensing. Stricter sensing constraints reduce the availability of position data, leading to degraded channel estimation and thus lower performance. We apply Lyapunov optimization to solve the problem and derive a dynamic sensing and beamforming algorithm. Numerical evaluations on the DeepSense and Raymobtime datasets show that halving sensing times leads to only up to 7.7% loss in average SNR.

Dynamic Joint Communications and Sensing Precoding Design: A Lyapunov Approach

This letter proposes a dynamic joint communications and sensing (JCAS) framework to adaptively design dedicated sensing and communications precoders. We first formulate a stochastic control problem to maximize the long-term average signal-to-noise ratio for sensing, subject to a minimum average communications signal-to-interference-plus-noise ratio requirement and a power budget. Using Lyapunov optimization, specifically the drift-plus-penalty method, we cast the problem into a sequence of per-slot non-convex problems. To solve these problems, we develop a successive convex approximation method. Additionally, we derive a closed-form solution to the per-slot problems based on the notion of zero-forcing. Numerical evaluations demonstrate the efficacy of the proposed methods and highlight their superiority compared to a baseline method based on conventional design.

Sphere Precoding for Robust Near-Field Communications

Near-field communication with large antenna arrays promises significant beamforming and multiplexing gains. These communication links, however, are very sensitive to user mobility as any small change in the user position may suddenly drop the signal power. This leads to critical challenges for the robustness of these near-field communication systems. In this paper, we propose \textit{sphere precoding}, which is a robust precoding design to address user mobility in near-field communications. To gain insights into the spatial correlation of near-field channels, we extend the one-ring channel model to what we call one-sphere channel model and derive the channel covariance considering user mobility. Based on the one-sphere channel model, a robust precoding design problem is defined to optimize the minimum signal-to-interference-plus-noise ratio (SINR) satisfaction probability among mobile users. By utilizing the eigen structure of channel covariance, we further design a relaxed convex problem to approximate the solution of the original non-convex problem. The low-complexity solution effectively shapes a sphere that maintains the signal power for the target user and also nulls its interference within spheres around the other users. Simulation results highlight the efficacy of the proposed solution in achieving robust precoding yet high achievable rates in near-field communication systems.

Hybrid MIMO in the Upper Mid-Band: Architectures, Processing, and Energy Efficiency

As 6G networks evolve, the upper mid-band spectrum (7 GHz to 24 GHz), or frequency range 3 (FR3), is emerging as a promising balance between the coverage offered by sub-6 GHz bands and the high-capacity of millimeter wave (mmWave) frequencies. This paper explores the structure of FR3 hybrid MIMO systems and proposes two architectural classes: Frequency Integrated (FI) and Frequency Partitioned (FP). FI architectures enhance spectral efficiency by exploiting multiple sub-bands parallelism, while FP architectures dynamically allocate sub-band access according to specific application requirements. Additionally, two approaches, fully digital (FD) and hybrid analog-digital (HAD), are considered, comparing shared (SRF) versus dedicated RF (DRF) chain configurations. Herein signal processing solutions are investigated, particularly for an uplink multi-user scenario with power control optimization. Results demonstrate that SRF and DRF architectures achieve comparable spectral efficiency; however, SRF structures consume nearly half the power of DRF in the considered setup. While FD architectures provide higher spectral efficiency, they do so at the cost of increased power consumption compared to HAD. Additionally, FI architectures show slightly greater power consumption compared to FP; however, they provide a significant benefit in spectral efficiency (over 4 x), emphasizing an important trade-off in FR3 engineering.