The evolution of 6G networks demands ultra-massive connectivity and intelligent radio environments, yet existing reconfigurable intelligent surface (RIS) technologies face critical limitations in hardware efficiency, dynamic control, and scalability. This paper introduces LLM-RIMSA, a transformative framework that integrates large language models (LLMs) with a novel reconfigurable intelligent metasurface antenna (RIMSA) architecture to address these challenges. Unlike conventional RIS designs, RIMSA employs parallel coaxial feeding and 2D metasurface integration, enabling each individual metamaterial element to independently adjust both its amplitude and phase. While traditional optimization and deep learning (DL) methods struggle with high-dimensional state spaces and prohibitive training costs for RIMSA control, LLM-RIMSA leverages pre-trained LLMs cross-modal reasoning and few-shot learning capabilities to dynamically optimize RIMSA configurations. Simulations demonstrate that LLM-RIMSA achieves state-of-the-art performance, outperforming conventional DL-based methods in sum rate while reducing training overhead. The proposed framework pave the way for LLM-driven intelligent radio environments.

Received signal strength (RSS)-based localization techniques have gained much attention in location-based services (LBSs). However, the coexistence of unknown path loss exponent (PLE), uncertain sensor positions, and impulsive noise poses serious challenges to localization accuracy. To address the problem, we first model the impulsive noise as a Mixture of Gaussian (MoG) distribution with unknown parameters. Thus, the noise model and the channel model can be refined using the observed data under the variational Bayesian inference (VBI) framework, which is defined as the model refinement learning. We then propose a corresponding online target localization procedure with the refined noise distribution, PLE and sensor positions. The Bayesian Cramer-Rao bound (BCRB) is finally derived in terms of all unknown parameters. Simulation results together with real experiment demonstrate that the proposed VBI algorithm can effectively learn the true noise distribution, and the developed localization method exhibits robust localization performance in various scenarios.

Received signal strength (RSS)-based WiFi fingerprint localization has attracted much attention for global positioning system denied-areas. Deep neural network (DNN) has introduced innovative techniques for indoor localization. However, deep learning models are susceptible to adversarial attacks, so the performance of indoor positioning methods is seriously threatened by adversarial attacks. To improve the localization performance, we first investigate the impact of adversarial attacks on indoor localization systems. A secure adversarial location guard framework, adv-LG, is then developed. It consists of a transformer-based generative adversarial network (TransGAN) and a cleaner module. TransGAN is developed to learn the mapping from adversarial samples to clean ones, while the cleaner module aims to remove adversarial perturbations from the adversarial samples using the learned mapping. The cleaned data is finally fed into a deep learning model to achieve online localization. We compare the localization performance of the proposed adv-LG method with adversarial training (AT), Gaussian smoothing (GS), and autoencoder (AE)-based approaches on two publicly available datasets, i.e., UJIIndoorLoc and UTSIndoorLoc. The results show that adv-LG exhibits significant advantages in classification and localization performance under several typical adversarial attack scenarios.

This paper investigates an intelligent reflecting surface (IRS) aided green multiple-user downlink communication system. In contrast to the existing works that deploy the IRS in a fixed location, the location of the IRS is taken as an optimization variable to minimize the total transmit power by jointly optimizing the location of the IRS, transmit beamformers at the base station (BS), and IRS phase shifts. We point out a critical conclusion that before and after IRS deployment, the channel state information (CSI) of all the communication terminals is different, so an offline-online hybrid-CSI optimization framework is proposed to solve the problem. In the offline stage, we optimize the IRS location with only the statistical CSI (S-CSI) so the ergodic quality of service (QoS) constraints have to be considered, and universal lower bounds associated only with the location variable are derived to decouple all variables. In the online stage, all the instantaneous-CSI (I-CSI) are available. To solve this non-convex problem, an alternating optimization framework is developed. We propose a Riemannian Manifold (RM) algorithm to optimize the IRS phase shifts. Simulation results validate that the proposed algorithm is convergent and effective, and show that the location deployment of IRS is crucial for green communication.