Tensor-Structured Bayesian Channel Prediction for Upper Mid-Band XL-MIMO Systems

The upper mid-band balances coverage and capacity for the future cellular systems and also embraces XL-MIMO systems, offering enhanced spectral and energy efficiency. However, these benefits are significantly degraded under mobility due to channel aging, and further exacerbated by the unique near-field (NF) and spatial non-stationarity (SnS) propagation in such systems. To address this challenge, we propose a novel channel prediction approach that incorporates dedicated channel modeling, probabilistic representations, and Bayesian inference algorithms for this emerging scenario. Specifically, we develop tensor-structured channel models in both the spatial-frequency-temporal (SFT) and beam-delay-Doppler (BDD) domains, which leverage temporal correlations among multiple pilot symbols for channel prediction. The factor matrices of multi-linear transformations are parameterized by BDD domain grids and SnS factors, where beam domain grids are jointly determined by angles and slopes under spatial-chirp based NF representations. To enable tractable inference, we replace environment-dependent BDD domain grids with uniformly sampled ones, and introduce perturbation parameters in each domain to mitigate grid mismatch. We further propose a hybrid beam domain strategy that integrates angle-only sampling with slope hyperparameterization to avoid the computational burden of explicit slope sampling. Based on the probabilistic models, we develop tensor-structured bi-layer inference (TS-BLI) algorithm under the expectation-maximization (EM) framework, which reduces computational complexity via tensor operations by leveraging the bi-layer factor graph for approximate E-step inference and an alternating strategy with closed-form updates in the M-step. Numerical simulations based on the near-practical channel simulator demonstrate the superior channel prediction performance of the proposed algorithm.

Free Energy-Inspired Cognitive Risk Integration for AV Navigation in Pedestrian-Rich Environments

Recent advances in autonomous vehicle (AV) behavior planning have shown impressive social interaction capabilities when interacting with other road users. However, achieving human-like prediction and decision-making in interactions with vulnerable road users remains a key challenge in complex multi-agent interactive environments. Existing research focuses primarily on crowd navigation for small mobile robots, which cannot be directly applied to AVs due to inherent differences in their decision-making strategies and dynamic boundaries. Moreover, pedestrians in these multi-agent simulations follow fixed behavior patterns that cannot dynamically respond to AV actions. To overcome these limitations, this paper proposes a novel framework for modeling interactions between the AV and multiple pedestrians. In this framework, a cognitive process modeling approach inspired by the Free Energy Principle is integrated into both the AV and pedestrian models to simulate more realistic interaction dynamics. Specifically, the proposed pedestrian Cognitive-Risk Social Force Model adjusts goal-directed and repulsive forces using a fused measure of cognitive uncertainty and physical risk to produce human-like trajectories. Meanwhile, the AV leverages this fused risk to construct a dynamic, risk-aware adjacency matrix for a Graph Convolutional Network within a Soft Actor-Critic architecture, allowing it to make more reasonable and informed decisions. Simulation results indicate that our proposed framework effectively improves safety, efficiency, and smoothness of AV navigation compared to the state-of-the-art method.

Interference in Spectrum-Sharing Integrated Terrestrial and Satellite Networks: Modeling, Approximation, and Robust Transmit Beamforming

This paper investigates robust transmit (TX) beamforming from the satellite to user terminals (UTs), based on statistical channel state information (CSI). The proposed design specifically targets the mitigation of satellite-to-terrestrial interference in spectrum-sharing integrated terrestrial and satellite networks. By leveraging the distribution information of terrestrial UTs, we first establish an interference model from the satellite to terrestrial systems without shared CSI. Based on this, robust TX beamforming schemes are developed under both the interference threshold and the power budget. Two optimization criteria are considered: satellite weighted sum rate maximization and mean square error minimization. The former achieves a superior achievable rate performance through an iterative optimization framework, whereas the latter enables a low-complexity closed-form solution at the expense of reduced rate, with interference constraints satisfied via a bisection method. To avoid complex integral calculations and the dependence on user distribution information in inter-system interference evaluations, we propose a terrestrial base station position-aided approximation method, and the approximation errors are subsequently analyzed. Numerical simulations validate the effectiveness of our proposed schemes.

MAC-Gaze: Motion-Aware Continual Calibration for Mobile Gaze Tracking

Mobile gaze tracking faces a fundamental challenge: maintaining accuracy as users naturally change their postures and device orientations. Traditional calibration approaches, like one-off, fail to adapt to these dynamic conditions, leading to degraded performance over time. We present MAC-Gaze, a Motion-Aware continual Calibration approach that leverages smartphone Inertial measurement unit (IMU) sensors and continual learning techniques to automatically detect changes in user motion states and update the gaze tracking model accordingly. Our system integrates a pre-trained visual gaze estimator and an IMU-based activity recognition model with a clustering-based hybrid decision-making mechanism that triggers recalibration when motion patterns deviate significantly from previously encountered states. To enable accumulative learning of new motion conditions while mitigating catastrophic forgetting, we employ replay-based continual learning, allowing the model to maintain performance across previously encountered motion conditions. We evaluate our system through extensive experiments on the publicly available RGBDGaze dataset and our own 10-hour multimodal MotionGaze dataset (481K+ images, 800K+ IMU readings), encompassing a wide range of postures under various motion conditions including sitting, standing, lying, and walking. Results demonstrate that our method reduces gaze estimation error by 19.9% on RGBDGaze (from 1.73 cm to 1.41 cm) and by 31.7% on MotionGaze (from 2.81 cm to 1.92 cm) compared to traditional calibration approaches. Our framework provides a robust solution for maintaining gaze estimation accuracy in mobile scenarios.

Time-Continuous Frequency Allocation for Feeder Links of Mega Constellations with Multi-Antenna Gateway Stations

With the recent rapid advancement of mega low earth orbit (LEO) satellite constellations, multi-antenna gateway station (MAGS) has emerged as a key enabler to support extremely high system capacity via massive feeder links. However, the densification of both space and ground segment leads to reduced spatial separation between links, posing unprecedented challenges of interference exacerbation. This paper investigates graph coloring-based frequency allocation methods for interference mitigation (IM) of mega LEO systems. We first reveal the characteristics of MAGS interference pattern and formulate the IM problem into a $K$-coloring problem using an adaptive threshold method. Then we propose two tailored graph coloring algorithms, namely Generalized Global (GG) and Clique-Based Tabu Search (CTS), to solve this problem. GG employs a low-complexity greedy conflict avoidance strategy, while CTS leverages the unique clique structure brought by MAGSs to enhance IM performance. Subsequently, we innovatively modify them to achieve time-continuous frequency allocation, which is crucial to ensure the stability of feeder links. Moreover, we further devise two mega constellation decomposition methods to alleviate the complexity burden of satellite operators. Finally, we propose a list coloring-based vacant subchannel utilization method to further improve spectrum efficiency and system capacity. Simulation results on Starlink constellation of the first and second generations with 34396 satellites demonstrate the effectiveness and superiority of the proposed methodology.

Extract the Best, Discard the Rest: CSI Feedback with Offline Large AI Models

Large AI models (LAMs) have shown strong potential in wireless communication tasks, but their practical deployment remains hindered by latency and computational constraints. In this work, we focus on the challenge of integrating LAMs into channel state information (CSI) feedback for frequency-division duplex (FDD) massive multiple-intput multiple-output (MIMO) systems. To this end, we propose two offline frameworks, namely site-specific LAM-enhanced CSI feedback (SSLCF) and multi-scenario LAM-enhanced CSI feedback (MSLCF), that incorporate LAMs into the codebook-based CSI feedback paradigm without requiring real-time inference. Specifically, SSLCF generates a site-specific enhanced codebook through fine-tuning on locally collected CSI data, while MSLCF improves generalization by pre-generating a set of environment-aware codebooks. Both of these frameworks build upon the LAM with vision-based backbone, which is pre-trained on large-scale image datasets and fine-tuned with CSI data to generate customized codebooks. This resulting network named LVM4CF captures the structural similarity between CSI and image, allowing the LAM to refine codewords tailored to the specific environments. To optimize the codebook refinement capability of LVM4CF under both single- and dual-side deployment modes, we further propose corresponding training and inference algorithms. Simulation results show that our frameworks significantly outperform existing schemes in both reconstruction accuracy and system throughput, without introducing additional inference latency or computational overhead. These results also support the core design methodology of our proposed frameworks, extracting the best and discarding the rest, as a promising pathway for integrating LAMs into future wireless systems.

Statistical CSI-Based Distributed Precoding Design for OFDM-Cooperative Multi-Satellite Systems

This paper investigates the design of distributed precoding for multi-satellite massive MIMO transmissions. We first conduct a detailed analysis of the transceiver model, in which delay and Doppler precompensation is introduced to ensure coherent transmission. In this analysis, we examine the impact of precompensation errors on the transmission model, emphasize the near-independence of inter-satellite interference, and ultimately derive the received signal model. Based on such signal model, we formulate an approximate expected rate maximization problem that considers both statistical channel state information (sCSI) and compensation errors. Unlike conventional approaches that recast such problems as weighted minimum mean square error (WMMSE) minimization, we demonstrate that this transformation fails to maintain equivalence in the considered scenario. To address this, we introduce an equivalent covariance decomposition-based WMMSE (CDWMMSE) formulation derived based on channel covariance matrix decomposition. Taking advantage of the channel characteristics, we develop a low-complexity decomposition method and propose an optimization algorithm. To further reduce computational complexity, we introduce a model-driven scalable deep learning (DL) approach that leverages the equivariance of the mapping from sCSI to the unknown variables in the optimal closed-form solution, enhancing performance through novel dense Transformer network and scaling-invariant loss function design. Simulation results validate the effectiveness and robustness of the proposed method in some practical scenarios. We also demonstrate that the DL approach can adapt to dynamic settings with varying numbers of users and satellites.

MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios

Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view images. In the proposed MLLM-SUL framework, a dual-branch visual encoder is first designed to extract features from two resolutions, and rich visual information is conducive to the language model describing risk objects of different sizes accurately. Then for the language generation, LLaMA model is fine-tuned to predict scene descriptions, containing the type of driving scenario, actions of risk objects, and driving intentions and suggestions of ego-vehicle. Ultimately, a transformer-based network incorporating a regression token is trained to locate the risk objects. Extensive experiments on the existing DRAMA-ROLISP dataset and the extended DRAMA-SRIS dataset demonstrate that our method is efficient, surpassing many state-of-the-art image-based and video-based methods. Specifically, our method achieves 80.1% BLEU-1 score and 298.5% CIDEr score in the scene understanding task, and 59.6% accuracy in the localization task. Codes and datasets are available at https://github.com/fjq-tongji/MLLM-SUL.

CovNet: Covariance Information-Assisted CSI Feedback for FDD Massive MIMO Systems

In this paper, we propose a novel covariance information-assisted channel state information (CSI) feedback scheme for frequency-division duplex (FDD) massive multi-input multi-output (MIMO) systems. Unlike most existing CSI feedback schemes, which rely on instantaneous CSI only, the proposed CovNet leverages CSI covariance information to achieve high-performance CSI reconstruction, primarily consisting of convolutional neural network (CNN) and Transformer architecture. To efficiently utilize covariance information, we propose a covariance information processing procedure and sophisticatedly design the covariance information processing network (CIPN) to further process it. Moreover, the feed-forward network (FFN) in CovNet is designed to jointly leverage the 2D characteristics of the CSI matrix in the angle and delay domains. Simulation results demonstrate that the proposed network effectively leverages covariance information and outperforms the state-of-the-art (SOTA) scheme across the full compression ratio (CR) range.

A Tensor-Structured Approach to Dynamic Channel Prediction for Massive MIMO Systems with Temporal Non-Stationarity

In moderate- to high-mobility scenarios, channel state information (CSI) varies rapidly and becomes temporally non-stationary, leading to significant performance degradation in channel reciprocity-dependent massive multiple-input multiple-output (MIMO) transmission. To address this challenge, we propose a tensor-structured approach to dynamic channel prediction (TS-DCP) for massive MIMO systems with temporal non-stationarity, leveraging dual-timescale and cross-domain correlations. Specifically, due to the inherent spatial consistency, non-stationary channels on long-timescales are treated as stationary on short-timescales, decoupling complicated correlations into more tractable dual-timescale ones. To exploit such property, we frame the pilot symbols, capturing short-timescale correlations within frames by Doppler domain modeling and long-timescale correlations across frames by Markov/autoregressive processes. Based on this, we develop the tensor-structured signal model in the spatial-frequency-temporal domain, incorporating correlated angle-delay-Doppler domain channels and Vandermonde-structured factor matrices. Furthermore, we model cross-domain correlations within each frame, arising from clustered scatterer distributions, using tensor-structured upgradations of Markov processes and coupled Gaussian distributions. Following these probabilistic models, we formulate the TS-DCP as the variational free energy (VFE) minimization problem, designing trial belief structures through online approximation and the Bethe method. This yields the online TS-DCP algorithm derived from a dual-layer VFE optimization process, where both outer and inner layers leverage the multilinear structure of channels to reduce computational complexity significantly. Numerical simulations demonstrate the significant superiority of the proposed algorithm over benchmarks in terms of channel prediction performance.