Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems

Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications, assisting with tasks including troubleshooting, standards interpretation, and network optimization. However, their deployment in practice must balance inference cost, latency, and reliability. In this work, we study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline. In it, an efficient edge model handles routine queries, a more capable cloud model addresses complex cases, and human experts are involved only when necessary. We define a misalignment-cost constrained optimization problem, aiming to minimize average processing cost, while guaranteeing alignment of automated answers with expert judgments. We propose a statistically rigorous threshold selection method based on multiple hypothesis testing (MHT) for a query processing mechanism based on knowledge and confidence tests. The approach provides finite-sample guarantees on misalignment risk. Experiments on the TeleQnA dataset -- a telecom-specific benchmark -- demonstrate that the proposed method achieves superior cost-efficiency compared to conventional cascaded baselines, while ensuring reliability at prescribed confidence levels.

Meta-SimGNN: Adaptive and Robust WiFi Localization Across Dynamic Configurations and Diverse Scenarios

To promote the practicality of deep learning-based localization, existing studies aim to address the issue of scenario dependence through meta-learning. However, these studies primarily focus on variations in environmental layouts while overlooking the impact of changes in device configurations, such as bandwidth, the number of access points (APs), and the number of antennas used. Unlike environmental changes, variations in device configurations affect the dimensionality of channel state information (CSI), thereby compromising neural network usability. To address this issue, we propose Meta-SimGNN, a novel WiFi localization system that integrates graph neural networks with meta-learning to improve localization generalization and robustness. First, we introduce a fine-grained CSI graph construction scheme, where each AP is treated as a graph node, allowing for adaptability to changes in the number of APs. To structure the features of each node, we propose an amplitude-phase fusion method and a feature extraction method. The former utilizes both amplitude and phase to construct CSI images, enhancing data reliability, while the latter extracts dimension-consistent features to address variations in bandwidth and the number of antennas. Second, a similarity-guided meta-learning strategy is developed to enhance adaptability in diverse scenarios. The initial model parameters for the fine-tuning stage are determined by comparing the similarity between the new scenario and historical scenarios, facilitating rapid adaptation of the model to the new localization scenario. Extensive experimental results over commodity WiFi devices in different scenarios show that Meta-SimGNN outperforms the baseline methods in terms of localization generalization and accuracy.

Sensing Framework Design and Performance Optimization with Action Detection for ISCC

Integrated sensing, communication, and computation (ISCC) has been regarded as a prospective technology for the next-generation wireless network, supporting humancentric intelligent applications. However, the delay sensitivity of these computation-intensive applications, especially in a multidevice ISCC system with limited resources, highlights the urgent need for efficient sensing task execution frameworks. To address this, we propose a resource-efficient sensing framework in this paper. Different from existing solutions, it features a novel action detection module deployed at each device to detect the onset of an action. Only time windows filled with signals of interest are offloaded to the edge server and processed by the edge recognition module, thus reducing overhead. Furthermore, we quantitatively analyze the sensing performance of the proposed sensing framework and formulate a sensing accuracy maximization problem under power, delay, and resource limitations for the multi-device ISCC system. By decomposing it into two subproblems, we develop an alternating direction method of multipliers (ADMM)-based distributed algorithm. It alternatively solves a sensing accuracy maximization subproblem at each device and employs a closed-form computation resource allocation strategy at the edge server till convergence. Finally, a real-world test is conducted using commodity wireless devices to validate the sensing performance analysis. Extensive test results demonstrate that our proposal achieves higher sensing accuracy under the limited resource compared to two baselines.

Online Conformal Probabilistic Numerics via Adaptive Edge-Cloud Offloading

Consider an edge computing setting in which a user submits queries for the solution of a linear system to an edge processor, which is subject to time-varying computing availability. The edge processor applies a probabilistic linear solver (PLS) so as to be able to respond to the user's query within the allotted time and computing budget. Feedback to the user is in the form of an uncertainty set. Due to model misspecification, the uncertainty set obtained via a direct application of PLS does not come with coverage guarantees with respect to the true solution of the linear system. This work introduces a new method to calibrate the uncertainty sets produced by PLS with the aim of guaranteeing long-term coverage requirements. The proposed method, referred to as online conformal prediction-PLS (OCP-PLS), assumes sporadic feedback from cloud to edge. This enables the online calibration of uncertainty thresholds via online conformal prediction (OCP), an online optimization method previously studied in the context of prediction models. The validity of OCP-PLS is verified via experiments that bring insights into trade-offs between coverage, prediction set size, and cloud usage.

Graph Neural Network for Location- and Orientation-Assisted mmWave Beam Alignment

In massive multi-input multi-output (MIMO) systems, the main bottlenecks of location- and orientation-assisted beam alignment using deep neural networks (DNNs) are large training overhead and significant performance degradation. This paper proposes a graph neural network (GNN)-based beam selection approach that reduces the training overhead and improves the alignment accuracy, by capitalizing on the strong expressive ability and few trainable parameters of GNN. The channels of beams are correlated according to the beam direction. Therefore, we establish a graph according to the angular correlation between beams and use GNN to capture the channel correlation between adjacent beams, which helps accelerate the learning process and enhance the beam alignment performance. Compared to existing DNN-based algorithms, the proposed method requires only 20\% of the dataset size to achieve equivalent accuracy and improves the Top-1 accuracy by 10\% when using the same dataset.

Joint Transmission and Deblurring: A Semantic Communication Approach Using Events

Deep learning-based joint source-channel coding (JSCC) is emerging as a promising technology for effective image transmission. However, most existing approaches focus on transmitting clear images, overlooking real-world challenges such as motion blur caused by camera shaking or fast-moving objects. Motion blur often degrades image quality, making transmission and reconstruction more challenging. Event cameras, which asynchronously record pixel intensity changes with extremely low latency, have shown great potential for motion deblurring tasks. However, the efficient transmission of the abundant data generated by event cameras remains a significant challenge. In this work, we propose a novel JSCC framework for the joint transmission of blurry images and events, aimed at achieving high-quality reconstructions under limited channel bandwidth. This approach is designed as a deblurring task-oriented JSCC system. Since RGB cameras and event cameras capture the same scene through different modalities, their outputs contain both shared and domain-specific information. To avoid repeatedly transmitting the shared information, we extract and transmit their shared information and domain-specific information, respectively. At the receiver, the received signals are processed by a deblurring decoder to generate clear images. Additionally, we introduce a multi-stage training strategy to train the proposed model. Simulation results demonstrate that our method significantly outperforms existing JSCC-based image transmission schemes, addressing motion blur effectively.

ROME: Robust Model Ensembling for Semantic Communication Against Semantic Jamming Attacks

Recently, semantic communication (SC) has garnered increasing attention for its efficiency, yet it remains vulnerable to semantic jamming attacks. These attacks entail introducing crafted perturbation signals to legitimate signals over the wireless channel, thereby misleading the receivers' semantic interpretation. This paper investigates the above issue from a practical perspective. Contrasting with previous studies focusing on power-fixed attacks, we extensively consider a more challenging scenario of power-variable attacks by devising an innovative attack model named Adjustable Perturbation Generator (APG), which is capable of generating semantic jamming signals of various power levels. To combat semantic jamming attacks, we propose a novel framework called Robust Model Ensembling (ROME) for secure semantic communication. Specifically, ROME can detect the presence of semantic jamming attacks and their power levels. When high-power jamming attacks are detected, ROME adapts to raise its robustness at the cost of generalization ability, and thus effectively accommodating the attacks. Furthermore, we theoretically analyze the robustness of the system, demonstrating its superiority in combating semantic jamming attacks via adaptive robustness. Simulation results show that the proposed ROME approach exhibits significant adaptability and delivers graceful robustness and generalization ability under power-variable semantic jamming attacks.

Towards Compatible Semantic Communication: A Perspective on Digital Coding and Modulation

Semantic communication (SC) is emerging as a pivotal innovation within the 6G framework, aimed at enabling more intelligent transmission. This development has led to numerous studies focused on designing advanced systems through powerful deep learning techniques. Nevertheless, many of these approaches envision an analog transmission manner by formulating the transmitted signals as continuous-valued semantic representation vectors, limiting their compatibility with existing digital systems. To enhance compatibility, it is essential to explore digitized SC systems. This article systematically identifies two promising paradigms for designing digital SC: probabilistic and deterministic approaches, according to the modulation strategies. For both, we first provide a comprehensive analysis of the methodologies. Then, we put forward the principles of designing digital SC systems with a specific focus on informativeness and robustness of semantic representations to enhance performance, along with constellation design. Additionally, we present a case study to demonstrate the effectiveness of these methods. Moreover, this article also explores the intrinsic advantages and opportunities provided by digital SC systems, and then outlines several potential research directions for future investigation.

Coarse-to-Fine: A Dual-Phase Channel-Adaptive Method for Wireless Image Transmission

Developing channel-adaptive deep joint source-channel coding (JSCC) systems is a critical challenge in wireless image transmission. While recent advancements have been made, most existing approaches are designed for static channel environments, limiting their ability to capture the dynamics of channel environments. As a result, their performance may degrade significantly in practical systems. In this paper, we consider time-varying block fading channels, where the transmission of a single image can experience multiple fading events. We propose a novel coarse-to-fine channel-adaptive JSCC framework (CFA-JSCC) that is designed to handle both significant fluctuations and rapid changes in wireless channels. Specifically, in the coarse-grained phase, CFA-JSCC utilizes the average signal-to-noise ratio (SNR) to adjust the encoding strategy, providing a preliminary adaptation to the prevailing channel conditions. Subsequently, in the fine-grained phase, CFA-JSCC leverages instantaneous SNR to dynamically refine the encoding strategy. This refinement is achieved by re-encoding the remaining channel symbols whenever the channel conditions change. Additionally, to reduce the overhead for SNR feedback, we utilize a limited set of channel quality indicators (CQIs) to represent the channel SNR and further propose a reinforcement learning (RL)-based CQI selection strategy to learn this mapping. This strategy incorporates a novel reward shaping scheme that provides intermediate rewards to facilitate the training process. Experimental results demonstrate that our CFA-JSCC provides enhanced flexibility in capturing channel variations and improved robustness in time-varying channel environments.

Learned Image Transmission with Hierarchical Variational Autoencoder

In this paper, we introduce an innovative hierarchical joint source-channel coding (HJSCC) framework for image transmission, utilizing a hierarchical variational autoencoder (VAE). Our approach leverages a combination of bottom-up and top-down paths at the transmitter to autoregressively generate multiple hierarchical representations of the original image. These representations are then directly mapped to channel symbols for transmission by the JSCC encoder. We extend this framework to scenarios with a feedback link, modeling transmission over a noisy channel as a probabilistic sampling process and deriving a novel generative formulation for JSCC with feedback. Compared with existing approaches, our proposed HJSCC provides enhanced adaptability by dynamically adjusting transmission bandwidth, encoding these representations into varying amounts of channel symbols. Additionally, we introduce a rate attention module to guide the JSCC encoder in optimizing its encoding strategy based on prior information. Extensive experiments on images of varying resolutions demonstrate that our proposed model outperforms existing baselines in rate-distortion performance and maintains robustness against channel noise.