Kaibin Huang

Tingyu Ding, Qunsong Zeng, Kaibin Huang

The development of sixth-generation (6G) mobile networks imposes unprecedented latency and reliability demands on multiple-input multiple-output (MIMO) communication systems, a key enabler of high-speed radio access. Recently, deep unfolding-based detectors, which map iterative algorithms onto neural network architectures, have emerged as a promising approach, combining the strengths of model-driven and data-driven methods to achieve high detection accuracy with relatively low complexity. However, algorithmic innovation alone is insufficient; software-hardware co-design is essential to meet the extreme latency requirements of 6G (i.e., 0.1 milliseconds). This motivates us to propose leveraging in-memory computing, which is an analog computing technology that integrates memory and computation within memristor circuits, to perform the intensive matrix-vector multiplication (MVM) operations inherent in deep MIMO detection at the nanosecond scale. Specifically, we introduce a novel architecture, called the deep in-memory MIMO (IM-MIMO) detector, characterized by two key features. First, each of its cascaded computational blocks is decomposed into channel-dependent and channel-independent neural network modules. Such a design minimizes the latency of memristor reprogramming in response to channel variations, which significantly exceeds computation time. Second, we develop a customized detector-training method that exploits prior knowledge of memristor-value statistics to enhance robustness against programming noise. Furthermore, we conduct a comprehensive analysis of the IM-MIMO detector's performance, evaluating detection accuracy, processing latency, and hardware complexity. Our study quantifies detection error as a function of various factors, including channel noise, memristor programming noise, and neural network size.

Dingzhu Wen, Yong Zhou, Xiaoyang Li et al.

The forthcoming generation of wireless technology, 6G, aims to usher in an era of ubiquitous intelligent services, where everything is interconnected and intelligent. This vision requires the seamless integration of three fundamental modules: Sensing for information acquisition, communication for information sharing, and computation for information processing and decision-making. These modules are intricately linked, especially in complex tasks such as edge learning and inference. However, the performance of these modules is interdependent, creating a resource competition for time, energy, and bandwidth. Existing techniques like integrated communication and computation (ICC), integrated sensing and computation (ISC), and integrated sensing and communication (ISAC) have made partial strides in addressing this challenge, but they fall short of meeting the extreme performance requirements. To overcome these limitations, it is essential to develop new techniques that comprehensively integrate sensing, communication, and computation. This integrated approach, known as Integrated Sensing, Communication, and Computation (ISCC), offers a systematic perspective for enhancing task performance. This paper begins with a comprehensive survey of historic and related techniques such as ICC, ISC, and ISAC, highlighting their strengths and limitations. It then discusses the benefits, functions, and challenges of ISCC. Subsequently, the state-of-the-art signal designs for ISCC, along with network resource management strategies specifically tailored for ISCC are explored. Furthermore, this paper discusses the exciting research opportunities that lie ahead for implementing ISCC in future advanced networks, and the unresolved issues requiring further investigation. ISCC is expected to unlock the full potential of intelligent connectivity, paving the way for groundbreaking applications and services.

Haotian Zheng, Zhanwei Wang, Mingyao Cui et al.

Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propose its distributed deployment to enable cooperative token generation in a multiuser edge system; its advantage is to effectively balance computational loads between resource-constrained devices and servers. The resulting architecture, termed Multi-access SPIN (Multi-SPIN), utilizes on-device small language models to generate and upload candidate token drafts, while an edge server operates the LLM to verify them in parallel batches. Given the severe heterogeneity in users' computation and communication capabilities, the draft length emerges as a critical control variable that influences node-level computation loads and multi-access latency, thereby governing the sum token goodput. Consequently, considering frequency-division multiple access, we investigate the problem of multi-access draft control, a joint optimization of draft-length control and bandwidth allocation to maximize sum token goodput. We examine two cases: (1) homogeneous draft lengths across users to facilitate server-side batching, and (2) heterogeneous draft lengths to introduce a new dimension for goodput enhancement. By developing decomposition methods, we reduce these complex optimizations into tractable sub-problems, which allow efficient draft control algorithms to be derived in closed form. Our analysis shows that the optimal bandwidth allocation compensates users with weaker computation-and-communication capabilities in the homogeneous case due to the batching synchronization requirements, whereas its heterogeneous-case counterpart rewards users with higher acceptance rates by relaxing such requirements. Experiments using Llama-2 and Qwen3.5 model pairs across diverse tasks demonstrate that Multi-SPIN improves goodput by up to 88% over heterogeneity-agnostic baselines.

Dingzhu Wen, Xiang Jiao, Peixi Liu et al.

Departing from the classic paradigm of data-centric designs, the 6G networks for supporting edge AI features task-oriented techniques that focus on effective and efficient execution of AI task. Targeting end-to-end system performance, such techniques are sophisticated as they aim to seamlessly integrate sensing (data acquisition), communication (data transmission), and computation (data processing). Aligned with the paradigm shift, a task-oriented over-the-air computation (AirComp) scheme is proposed in this paper for multi-device split-inference system. In the considered system, local feature vectors, which are extracted from the real-time noisy sensory data on devices, are aggregated over-the-air by exploiting the waveform superposition in a multiuser channel. Then the aggregated features as received at a server are fed into an inference model with the result used for decision making or control of actuators. To design inference-oriented AirComp, the transmit precoders at edge devices and receive beamforming at edge server are jointly optimized to rein in the aggregation error and maximize the inference accuracy. The problem is made tractable by measuring the inference accuracy using a surrogate metric called discriminant gain, which measures the discernibility of two object classes in the application of object/event classification. It is discovered that the conventional AirComp beamforming design for minimizing the mean square error in generic AirComp with respect to the noiseless case may not lead to the optimal classification accuracy. The reason is due to the overlooking of the fact that feature dimensions have different sensitivity towards aggregation errors and are thus of different importance levels for classification. This issue is addressed in this work via a new task-oriented AirComp scheme designed by directly maximizing the derived discriminant gain.

Zhengyang Hu, Yanzhi Chen, Hanxiang Ren et al.

Measuring statistical dependency between high-dimensional random variables is a fundamental task in data science and machine learning. Neural mutual information (MI) estimators offer a promising avenue, but they typically require costly iterative optimization for each new dataset, making them impractical for real-time applications. We present InfoAtlas, a foundation model-like architecture that eliminates this bottleneck by directly inferring MI in a single forward pass. Pretrained on large-scale synthetic data with rich dependence patterns, InfoAtlas learns to identify diverse dependence structures and predict MI directly from the dataset. Comprehensive experiments demonstrate that InfoAtlas matches state-of-the-art neural estimators in accuracy while achieving $100\times$ speedup, can flexibly handle varying dimensions and sample sizes through a single unified model, and generalizes effectively to complex, real-world scenarios. By reformulating MI estimation as an inference task, InfoAtlas establishes a foundation for real-time dependency analysis.

Zheng Lin, Guangyu Zhu, Yiqin Deng et al.

The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices. To overcome this challenge, in this paper, we advocate the integration of edge computing paradigm and parallel split learning (PSL), allowing multiple client devices to offload substantial training workloads to an edge server via layer-wise model split. By observing that existing PSL schemes incur excessive training latency and large volume of data transmissions, we propose an innovative PSL framework, namely, efficient parallel split learning (EPSL), to accelerate model training. To be specific, EPSL parallelizes client-side model training and reduces the dimension of local gradients for back propagation (BP) via last-layer gradient aggregation, leading to a significant reduction in server-side training and communication latency. Moreover, by considering the heterogeneous channel conditions and computing capabilities at client devices, we jointly optimize subchannel allocation, power control, and cut layer selection to minimize the per-round latency. Simulation results show that the proposed EPSL framework significantly decreases the training latency needed to achieve a target accuracy compared with the state-of-the-art benchmarks, and the tailored resource management and layer split strategy can considerably reduce latency than the counterpart without optimization.

Kaibin Huang, Hai Wu, Zhiyan Liu et al.

The sixth-generation (6G) mobile networks are expected to feature the ubiquitous deployment of machine learning and AI algorithms at the network edge. With rapid advancements in edge AI, the time has come to realize intelligence downloading onto edge devices (e.g., smartphones and sensors). To materialize this version, we propose a novel technology in this article, called in-situ model downloading, that aims to achieve transparent and real-time replacement of on-device AI models by downloading from an AI library in the network. Its distinctive feature is the adaptation of downloading to time-varying situations (e.g., application, location, and time), devices' heterogeneous storage-and-computing capacities, and channel states. A key component of the presented framework is a set of techniques that dynamically compress a downloaded model at the depth-level, parameter-level, or bit-level to support adaptive model downloading. We further propose a virtualized 6G network architecture customized for deploying in-situ model downloading with the key feature of a three-tier (edge, local, and central) AI library. Furthermore, experiments are conducted to quantify 6G connectivity requirements and research opportunities pertaining to the proposed technology are discussed.

Zheng Lin, Guanqiao Qu, Xianhao Chen et al.

With the proliferation of distributed edge computing resources, the 6G mobile network will evolve into a network for connected intelligence. Along this line, the proposal to incorporate federated learning into the mobile edge has gained considerable interest in recent years. However, the deployment of federated learning faces substantial challenges as massive resource-limited IoT devices can hardly support on-device model training. This leads to the emergence of split learning (SL) which enables servers to handle the major training workload while still enhancing data privacy. In this article, we offer a brief overview of key advancements in SL and articulate its seamless integration with wireless edge networks. We begin by illustrating the tailored 6G architecture to support edge SL. Then, we examine the critical design issues for edge SL, including innovative resource-efficient learning frameworks and resource management strategies under a single edge server. Additionally, we expand the scope to multi-edge scenarios, exploring multi-edge collaboration and mobility management from a networking perspective. Finally, we discuss open problems for edge SL, including convergence analysis, asynchronous SL and U-shaped SL.

Hong Xing, Guangxu Zhu, Dongzhu Liu et al.

With the advent of emerging IoT applications such as autonomous driving, digital-twin and metaverse etc. featuring massive data sensing, analyzing and inference as well critical latency in beyond 5G (B5G) networks, edge artificial intelligence (AI) has been proposed to provide high-performance computation of a conventional cloud down to the network edge. Recently, convergence of wireless sensing, computation and communication (SC${}^2$) for specific edge AI tasks, has aroused paradigm shift by enabling (partial) sharing of the radio-frequency (RF) transceivers and information processing pipelines among these three fundamental functionalities of IoT. However, most existing design frameworks separate these designs incurring unnecessary signaling overhead and waste of energy, and it is therefore of paramount importance to advance fully integrated sensing, computation and communication (ISCC) to achieve ultra-reliable and low-latency edge intelligence acquisition. In this article, we provide an overview of principles of enabling ISCC technologies followed by two concrete use cases of edge AI tasks demonstrating the advantage of task-oriented ISCC, and pointed out some practical challenges in edge AI design with advanced ISCC solutions.

Baofu Han, Bing Li, Yining Qi et al.

Privacy-Preserving Federated Learning (PPFL) has emerged as a secure distributed Machine Learning (ML) paradigm that aggregates locally trained gradients without exposing raw data. To defend against model poisoning threats, several robustness-enhanced PPFL schemes have been proposed by integrating anomaly detection. Nevertheless, they still face two major challenges: (1) the reliance on heavyweight encryption techniques results in substantial communication and computation overhead; and (2) single-strategy defense mechanisms often fail to provide sufficient robustness against adaptive adversaries. To overcome these challenges, we propose DP2Guard, a lightweight PPFL framework that enhances both privacy and robustness. DP2Guard leverages a lightweight gradient masking mechanism to replace costly cryptographic operations while ensuring the privacy of local gradients. A hybrid defense strategy is proposed, which extracts gradient features using singular value decomposition and cosine similarity, and applies a clustering algorithm to effectively identify malicious gradients. Additionally, DP2Guard adopts a trust score-based adaptive aggregation scheme that adjusts client weights according to historical behavior, while blockchain records aggregated results and trust scores to ensure tamper-proof and auditable training. Extensive experiments conducted on two public datasets demonstrate that DP2Guard effectively defends against four advanced poisoning attacks while ensuring privacy with reduced communication and computation costs.

Hai Wu, Ruifei He, Haoru Tan et al.

Although considerable progress has been obtained in neural network quantization for efficient inference, existing methods are not scalable to heterogeneous devices as one dedicated model needs to be trained, transmitted, and stored for one specific hardware setting, incurring considerable costs in model training and maintenance. In this paper, we study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. With this representation, we can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model. To this end, we propose a simple once quantization-aware training (QAT) scheme for obtaining high-performance vertical-layered models. Our design incorporates a cascade downsampling mechanism which allows us to obtain multiple quantized networks from one full precision source model by progressively mapping the higher precision weights to their adjacent lower precision counterparts. Then, with networks of different bit-widths from one source model, multi-objective optimization is employed to train the shared source model weights such that they can be updated simultaneously, considering the performance of all networks. By doing this, the shared weights will be optimized to balance the performance of different quantized models, thus making the weights transferable among different bit widths. Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width. Code will be available.

Zheng Lin, Guanqiao Qu, Qiyuan Chen et al.

Large language models (LLMs), which have shown remarkable capabilities, are revolutionizing AI development and potentially shaping our future. However, given their multimodality, the status quo cloud-based deployment faces some critical challenges: 1) long response time; 2) high bandwidth costs; and 3) the violation of data privacy. 6G mobile edge computing (MEC) systems may resolve these pressing issues. In this article, we explore the potential of deploying LLMs at the 6G edge. We start by introducing killer applications powered by multimodal LLMs, including robotics and healthcare, to highlight the need for deploying LLMs in the vicinity of end users. Then, we identify the critical challenges for LLM deployment at the edge and envision the 6G MEC architecture for LLMs. Furthermore, we delve into two design aspects, i.e., edge training and edge inference for LLMs. In both aspects, considering the inherent resource limitations at the edge, we discuss various cutting-edge techniques, including split learning/inference, parameter-efficient fine-tuning, quantization, and parameter-sharing inference, to facilitate the efficient deployment of LLMs. This article serves as a position paper for thoroughly identifying the motivation, challenges, and pathway for empowering LLMs at the 6G edge.

Guanqiao Qu, Qiyuan Chen, Wei Wei et al.

On-device large language models (LLMs), referring to running LLMs on edge devices, have raised considerable interest since they are more cost-effective, latency-efficient, and privacy-preserving compared with the cloud paradigm. Nonetheless, the performance of on-device LLMs is intrinsically constrained by resource limitations on edge devices. Sitting between cloud and on-device AI, mobile edge intelligence (MEI) presents a viable solution by provisioning AI capabilities at the edge of mobile networks, enabling end users to offload heavy AI computation to capable edge servers nearby. This article provides a contemporary survey on harnessing MEI for LLMs. We begin by illustrating several killer applications to demonstrate the urgent need for deploying LLMs at the network edge. Next, we present the preliminaries of LLMs and MEI, followed by resource-efficient LLM techniques. We then present an architectural overview of MEI for LLMs (MEI4LLM), outlining its core components and how it supports the deployment of LLMs. Subsequently, we delve into various aspects of MEI4LLM, extensively covering edge LLM caching and delivery, edge LLM training, and edge LLM inference. Finally, we identify future research opportunities. We hope this article inspires researchers in the field to leverage mobile edge computing to facilitate LLM deployment, thereby unleashing the potential of LLMs across various privacy- and delay-sensitive applications.

Fenghao Zhu, Xinquan Wang, Siming Jiang et al.

The emergence of sixth-generation and beyond communication systems is expected to fundamentally transform digital experiences through introducing unparalleled levels of intelligence, efficiency, and connectivity. A promising technology poised to enable this revolutionary vision is a wireless large AI model (WLAM), characterized by its exceptional capabilities in data processing, inference, and decision-making. In light of these remarkable capabilities, this paper provides a comprehensive survey of WLAM, explaining its fundamental principles, diverse applications, critical challenges, and future research opportunities. We begin by introducing the background of WLAM and analyzing the key synergies with wireless networks, emphasizing the mutual benefits. Subsequently, we explore the foundational characteristics of WLAM, delving into their unique relevance in wireless environments. Then, the role of WLAM in optimizing wireless communication systems across various use cases and the reciprocal benefits are systematically investigated. Furthermore, we discuss the integration of WLAM with emerging technologies, highlighting their potential to enable transformative capabilities and breakthroughs in wireless communication. Finally, we thoroughly examine the high-level challenges and discuss pivotal future research directions.

Guanqiao Qu, Zheng Lin, Qian Chen et al.

Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm of edge model caching. In this paper, we develop a novel model placement framework, called parameter-sharing model caching (TrimCaching). TrimCaching exploits the key observation that a wide range of AI models, such as convolutional neural networks or large language models, can share a significant proportion of parameter blocks containing reusable knowledge, thereby improving storage efficiency. To this end, we formulate a parameter-sharing model placement problem to maximize the cache hit ratio in multi-edge wireless networks by balancing the fundamental tradeoff between storage efficiency and service latency. We show that the formulated problem is a submodular maximization problem with submodular constraints, for which no polynomial-time approximation algorithm exists. To tackle this challenge, we study an important special case, where a small fixed number of parameter blocks are shared across models, which often holds in practice. In such a case, a polynomial-time algorithm with a $\left(1-ε\right)/2$-approximation guarantee is developed. Subsequently, we address the original problem for the general case by developing a greedy algorithm. Simulation results demonstrate that the proposed TrimCaching framework significantly improves the cache hit ratio compared with state-of-the-art content caching without exploiting shared parameters in AI models.

Hai Wu, Qunsong Zeng, Kaibin Huang

For the 6G mobile networks, in-situ model downloading has emerged as an important use case to enable real-time adaptive artificial intelligence on edge devices. However, the simultaneous downloading of diverse and high-dimensional models to multiple devices over wireless links presents a significant communication bottleneck. To overcome the bottleneck, we propose the framework of model broadcasting and assembling (MBA), which represents the first attempt on leveraging reusable knowledge, referring to shared parameters among tasks, to enable parameter broadcasting to reduce communication overhead. The MBA framework comprises two key components. The first, the MBA protocol, defines the system operations including parameter selection from a model library, power control for broadcasting, and model assembling at devices. The second component is the joint design of parameter-selection-and-power-control (PS-PC), which provides guarantees on devices' model performance and minimizes the downloading latency. The corresponding optimization problem is simplified by decomposition into the sequential PS and PC sub-problems without compromising its optimality. The PS sub-problem is solved efficiently by designing two efficient algorithms. On one hand, the low-complexity algorithm of greedy parameter selection features the construction of candidate model sets and a selection metric, both of which are designed under the criterion of maximum reusable knowledge among tasks. On the other hand, the optimal tree-search algorithm gains its efficiency via the proposed construction of a compact binary tree pruned using model architecture constraints and an intelligent branch-and-bound search. Given optimal PS, the optimal PC policy is derived in closed form. Extensive experiments demonstrate the substantial reduction in downloading latency achieved by the proposed MBA compared to traditional model downloading.

Shanfeng Huang, Zezhong Zhang, Shuai Wang et al.

Federated edge learning (FEEL) is envisioned as a promising paradigm to achieve privacy-preserving distributed learning. However, it consumes excessive learning time due to the existence of straggler devices. In this paper, a novel topology-optimized federated edge learning (TOFEL) scheme is proposed to tackle the heterogeneity issue in federated learning and to improve the communication-and-computation efficiency. Specifically, a problem of jointly optimizing the aggregation topology and computing speed is formulated to minimize the weighted summation of energy consumption and latency. To solve the mixed-integer nonlinear problem, we propose a novel solution method of penalty-based successive convex approximation, which converges to a stationary point of the primal problem under mild conditions. To facilitate real-time decision making, an imitation-learning based method is developed, where deep neural networks (DNNs) are trained offline to mimic the penalty-based method, and the trained imitation DNNs are deployed at the edge devices for online inference. Thereby, an efficient imitate-learning based approach is seamlessly integrated into the TOFEL framework. Simulation results demonstrate that the proposed TOFEL scheme accelerates the federated learning process, and achieves a higher energy efficiency. Moreover, we apply the scheme to 3D object detection with multi-vehicle point cloud datasets in the CARLA simulator. The results confirm the superior learning performance of the TOFEL scheme over conventional designs with the same resource and deadline constraints.

Zhanwei Wang, Huiling Yang, Min Sheng et al.

Leveraging continuous solar energy harvesting at high efficiency, space data centers are envisioned as a promising platform for executing energy-intensive large language models (LLMs). Recognizing this advantage, space and AI conglomerates (e.g., SpaceX, Google) are actively investing in this vision. One key challenge, however, is the efficient distributed deployment of a large-scale LLM in a satellite network due to the limited onboard computing and communication resources. This gives rise to a placement problem that involves partitioning and mapping model components to satellites such that the fundamentally different model architecture and network topology can be reconciled to ensure low-latency token generation. To address this problem, we present the Space Network of Experts (Space-XNet) framework targeting the distributed execution of a popular mixture-of-experts (MoE) model in space. The proposed placement strategies are two-level: (1) layer placement, which assigns MoE layers to satellite subnets; and (2) intra-layer expert placement, which assigns individual experts to satellites associated with the same layer/subnet. For layer placement, we exploit the ring-like communication pattern of autoregressive inference to partition the satellite constellation along the orbiting direction into subnets arranged on a ring, each hosting one MoE layer. Based on this architecture, we formulate and solve an optimization problem for intra-layer expert placement to map experts with heterogeneous activation probabilities onto satellites. The derived strategy reveals an intuitive principle: a frequently activated expert should be mapped to a satellite on a routing path with low expected latency. Experiments over a thousand-satellite constellation show that Space-XNet achieves at least a threefold latency reduction compared with conventional random and ablation-based placement strategies.

Nuocheng Yang, Sihua Wang, Zhaohui Yang et al.

Distributed Federated Learning (DFL) enables decentralized model training across large-scale systems without a central parameter server. However, DFL faces three critical challenges: privacy leakage from honest-but-curious neighbors, slow convergence due to the lack of central coordination, and vulnerability to Byzantine adversaries aiming to degrade model accuracy. To address these issues, we propose a novel DFL framework that integrates Byzantine robustness, privacy preservation, and convergence acceleration. Within this framework, each device trains a local model using a Bayesian approach and independently selects an optimal subset of neighbors for posterior exchange. We formulate this neighbor selection as an optimization problem to minimize the global loss function under security and privacy constraints. Solving this problem is challenging because devices only possess partial network information, and the complex coupling between topology, security, and convergence remains unclear. To bridge this gap, we first analytically characterize the trade-offs between dynamic connectivity, Byzantine detection, privacy levels, and convergence speed. Leveraging these insights, we develop a fully distributed Graph Neural Network (GNN)-based Reinforcement Learning (RL) algorithm. This approach enables devices to make autonomous connection decisions based on local observations. Simulation results demonstrate that our method achieves superior robustness and efficiency with significantly lower overhead compared to traditional security and privacy schemes.

Hai Wu, Xu Chen, Kaibin Huang

The emergence of large-scale foundation models (FoMo's) that can perform human-like intelligence motivates their deployment at the network edge for devices to access state-of-the-art artificial intelligence. For better user experiences, the pre-trained FoMo's need to be adapted to specialized downstream tasks through fine-tuning techniques. To transcend a single device's memory and computation limitations, we advocate multi-device cooperation within the device-edge cooperative fine-tuning (DEFT) paradigm, where edge devices cooperate to simultaneously optimize different parts of fine-tuning parameters within a FoMo. However, the parameter blocks reside at different depths within a FoMo architecture, leading to varied computation latency-and-memory cost due to gradient backpropagation-based calculations. The heterogeneous on-device computation and memory capacities and channel conditions necessitate an integrated communication-and-computation allocation of local computation loads and communication resources to achieve low-latency (LoLa) DEFT. To this end, we consider the depth-ware DEFT block allocation problem. The involved optimal block-device matching is tackled by the proposed low-complexity Cutting-RecoUNting-CHecking (CRUNCH) algorithm, which is designed by exploiting the monotone-increasing property between block depth and computation latency-and-memory cost. Next, the joint bandwidth-and-block allocation makes the problem more sophisticated. We observe a splittable Lagrangian expression through the transformation and analysis of the original problem, where the variables indicating device involvement are introduced. Then, the dual ascent method is employed to tackle this problem iteratively. Through extensive experiments conducted on the GLUE benchmark, our results demonstrate significant latency reduction achievable by LoLa DEFT for fine-tuning a RoBERTa model.

Qian Chen, Xianhao Chen, Min Sheng et al.

As satellite networks evolve to support increasingly diverse services and artificial general intelligence (AGI), large language models (LLMs) are emerging as a critical foundation for future space systems. However, deploying LLMs on satellites is hindered by stringent constraints on onboard memory, computation, and energy. In this context, the mixture-of-experts (MoE) architecture emerges as a promising solution, leveraging sparse expert activation to enable scalable model inference. By harnessing the architectural advantages of MoE, this article provides a comprehensive overview of SpaceMoE, a new paradigm for distributed MoE inference in satellite networks. We first review recent industrial progress and emerging standardization trends that motivate the evolution toward space AGI systems. Then, we introduce the fundamentals and architectural evolution of SpaceMoE. Subsequently, we discuss three fundamental design problems in SpaceMoE, namely expert placement, expert selection, and hidden-state transmission and routing, highlighting how satellite-specific factors such as dynamic topology, battery degradation, and thermal limits fundamentally reshape their solutions. Finally, we outline promising research directions for realizing scalable, efficient, and sustainable on-orbit MoE inference in future satellite networks.

Seyed Mohammad Azimi-Abarghouyi, Carlo Fischione, Kaibin Huang

Over-the-Air Federated Learning (AirFL) is an emerging paradigm that tightly integrates wireless signal processing and distributed machine learning to enable scalable AI at the network edge. By leveraging the superposition property of wireless signals, AirFL performs communication and model aggregation of the learning process simultaneously, significantly reducing latency, bandwidth, and energy consumption. This article offers a tutorial treatment of AirFL, presenting a novel classification into three design approaches: CSIT-aware, blind, and weighted AirFL. We provide a comprehensive guide to theoretical foundations, performance analysis, complexity considerations, practical limitations, and prospective research directions.

Songhan Zhao, Shimin Gong, Bo Gu et al.

This paper explores a reconfigurable intelligent surface (RIS)-assisted and semantic-aware wireless network, where multiple semantic users (SUs) transmit semantic information to an access point (AP) using the non-orthogonal multiple access (NOMA) method. The RIS reconfigures channel conditions, while semantic extraction reshapes traffic demands, providing enhanced control flexibility for NOMA transmissions. To enable efficient long-term resource allocation, we propose a deferrable semantic extraction scheme that can distribute the semantic extraction tasks across multiple time slots. We formulate a long-term energy efficiency maximization problem by jointly optimizing the RIS's passive beamforming, the SUs' semantic extraction, and the NOMA decoding order. Note that this problem involves multiple and coupled control variables, which can incur significant computational overhead in time-varying network environments. To support low-complexity online optimization, a deep reinforcement learning (DRL)-driven online optimization framework is developed. Specifically, the DRL module facilitates the adaptive selection and optimization of the most suitable option from traffic reshaping, channel reconfiguration, or NOMA decoding order assignment based on the dynamic network status. Numerical results demonstrate that the deferrable semantic extraction scheme significantly improves the long-term energy efficiency. Meanwhile, the DRL-driven online optimization framework effectively reduces the running time while maintaining superior learning performance compared to state-of-the-art methods.

Shunpu Tang, Qianqian Yang, Jihong Park et al.

Learning-based semantic communication (SemCom) has recently emerged as a promising paradigm for improving the transmission efficiency of wireless networks. However, existing methods typically rely on extensive end-to-end training, which is both inflexible and computationally expensive in dynamic wireless environments. Moreover, they fail to exploit redundancy across multiple transmissions of semantically similar content, limiting overall efficiency. To overcome these limitations, we propose a channel-aware generative adversarial network (GAN) inversion-based joint source-channel coding (CAGI-JSCC) framework that enables training-free SemCom by leveraging a pre-trained SemanticStyleGAN model. By explicitly incorporating wireless channel characteristics into the GAN inversion process, CAGI-JSCC adapts to varying channel conditions without additional training. Furthermore, we introduce a cache-enabled dynamic codebook (CDC) that caches disentangled semantic components at both the transmitter and receiver, allowing the system to reuse previously transmitted content. This semantic-level caching can continuously reduce redundant transmissions as experience accumulates. Extensive experiments on image transmission demonstrate the effectiveness of the proposed framework. In particular, our system achieves comparable perceptual quality with an average bandwidth compression ratio (BCR) of 1/224, and as low as 1/1024 for a single image, significantly outperforming baselines with a BCR of 1/128.

Zhouxiang Zhao, Jiaxiang Wang, Yahao Ding et al.

Efficient digital twin (DT) synchronization relies on maintaining high-fidelity virtual representations with minimal age of information (AoI). However, the synergistic potential of cooperative sensing and autonomous mobility of the sensing agent remains underexplored in existing DT synchronization frameworks. In this paper, we propose an agentic AI-empowered mobile embodied AI network (MEAN) framework for DT synchronization. In the proposed hybrid architecture, the base station (BS) conducts global orchestration, while the agents autonomously execute a five-stage closed-loop workflow: move-to-sense, cooperative sensing, onboard semantic processing, channel-aware mobility, and uplink transmission. To optimize synchronization performance, we formulate a joint topology dispatching and multidimensional resource allocation problem aimed at minimizing the maximum twin deviation across regions, subject to heterogeneous sensing fidelity and energy budget constraints. To tackle this, we develop a hierarchical two-layer optimization algorithm, where the outer-layer refines multi-agent assignment via a dynamic matching game, and the inner-layer iteratively optimizes the continuous resources. Extensive simulation results verify the convergence of the proposed algorithm and demonstrate its substantial superiority over multiple baseline schemes in reducing synchronization deviation. Furthermore, the results reveal that semantic compression serves as a vital substitute for channel resources in latency reduction under constrained bandwidth, while autonomous velocity adaptation provides an essential degree of freedom for the system to navigate the fundamental energy-time trade-off.

Shiyuan Zhang, Jiale Du, Yuanwei Liu et al.

Base station (BS) deployment and operation are fundamental to network performance, yet they require accurate demand understanding, which remains difficult for operators. Cellular traffic in dense urban regions is well measured but highly dynamic, which undermines prediction-based management, whereas the scarcity of traffic measurements in emerging regions limits informed deployment decisions. Existing approaches therefore either depend on manual planning heuristics or use autoregressive predictors that fail to capture stochastic traffic variation. We present NetSpatial, a unified system for cellular planning and operation through spatially conditional traffic generation. NetSpatial exploits multimodal urban context, including satellite imagery and point of interest (POI) distributions, to learn how physical environment and functional semantics shape BS demand. It uses a multi-level flow-matching architecture that separates periodic structure from residual dynamics, enabling direct generation of long-horizon traffic sequences. NetSpatial supports two complementary decision scenarios, i.e., what-if analysis for deployment planning, which ranks candidate sites using generated traffic profiles, and what-to-do support for network operation, which uses generated traffic forecasts to guide BS sleep scheduling and load balancing. Experiments on real-world cellular traffic data show that NetSpatial reduces Jensen-Shannon Divergence (JSD) by 29.44% over the strongest baseline, generalizes across cities in zero-shot experiments, and enables up to 16.8% energy savings while maintaining over 80% quality of experience.

Runxin Zhang, Yulin Shao, Hongyu An et al.

Semantic communication, enabled by deep joint source-channel coding (DeepJSCC), is widely expected to inherit the vulnerability of deep learning to adversarial perturbations. This paper challenges this prevailing belief and reveals a counterintuitive finding: semantic communication systems exhibit unanticipated adversarial robustness that can exceed that of classical separate source-channel coding systems. On the theoretical front, we establish fundamental bounds on the minimum attack power required to induce a target distortion, overcoming the analytical intractability of highly nonlinear DeepJSCC models by leveraging Lipschitz smoothness. We prove that the implicit regularization from noisy training forces decoder smoothness, a property that inherently provides built-in protection against adversarial attacks. To enable rigorous and fair comparison, we develop two novel attack methodologies that address previously unexplored vulnerabilities: a structure-aware vulnerable set attack that, for the first time, exploits graph-theoretic vulnerabilities in LDPC codes to induce decoding failure with minimal energy, and a progressive gradient ascent attack that leverages the differentiability of DeepJSCC to efficiently find minimum-power perturbations. Designing such attacks is challenging, as classical systems lack gradient information while semantic systems require navigating high-dimensional, non-convex spaces; our methods fill these critical gaps in the literature. Extensive experiments demonstrate that semantic communication requires up to $14$-$16\times$ more attack power to achieve the same distortion as classical systems, empirically substantiating its superior robustness.

Yun Tian, Zhijin Qin, Guocheng Lv et al.

Existing speech semantic communication systems mainly based on Joint Source-Channel Coding (JSCC) architectures have demonstrated impressive performance, but their effectiveness remains limited by model structures specifically designed for particular tasks and datasets. Recent advances indicate that generative large models pre-trained on massive datasets, can achieve outstanding performance arexhibit exceptional performance across diverse downstream tasks with minimal fine-tuning. To exploit the rich semantic knowledge embedded in large models and enable adaptive transmission over lossy channels, we propose a Large Speech Model enabled Semantic Communication (LargeSC) system. Simultaneously achieving adaptive compression and robust transmission over lossy channels remains challenging, requiring trade-offs among compression efficiency, speech quality, and latency. In this work, we employ the Mimi as a speech codec, converting speech into discrete tokens compatible with existing network architectures. We propose an adaptive controller module that enables adaptive transmission and in-band Unequal Error Protection (UEP), dynamically adjusting to both speech content and packet loss probability under bandwidth constraints. Additionally, we employ Low-Rank Adaptation (LoRA) to finetune the Moshi foundation model for generative recovery of lost speech tokens. Simulation results show that the proposed system supports bandwidths ranging from 550 bps to 2.06 kbps, outperforms conventional baselines in speech quality under high packet loss rates and achieves an end-to-end latency of approximately 460 ms, thereby demonstrating its potential for real-time deployment.

Qian Chen, Xianhao Chen, Kaibin Huang

Mixture-of-Experts (MoE) architectures leverage sparse activation to enhance the scalability of large language models (LLMs), making them suitable for deployment in resource-constrained edge networks. However, the sheer number of experts often exceeds the memory capacity of individual edge nodes, necessitating wireless distributed MoE (WIDE) inference where experts are spread across multiple edge nodes. In this context, expert selection directly affects communication costs. Motivated by the similarity of experts, we propose SiftMoE, which judiciously selects or skips experts to strike a tradeoff between communication costs and inference accuracy. Specifically, we first establish theoretical bounds on the accuracy degradation resulting from expert replacement or skipping. Based on the bounds, we formulate an energy minimization problem for expert selection in WIDE inference subject to latency and accuracy constraints. In particular, for slow-fading channels, we derive optimal expert selection policies for both single-token decoding and multi-token prefilling. For fast-fading channels, we further extend our scheme to cope with rapidly varying channel conditions. Simulation results demonstrate that SiftMoE significantly reduces energy consumption while maintaining inference accuracy compared with conventional Top-K routing in WIDE systems.

Shiyuan Zhang, Tong Li, Zhu Xiao et al.

Service-level mobile traffic prediction for individual users is essential for network efficiency and quality of service enhancement. However, current prediction methods are limited in their adaptability across different urban environments and produce inaccurate results due to the high uncertainty in personal traffic patterns, the lack of detailed environmental context, and the complex dependencies among different network services. These challenges demand advanced modeling techniques that can capture dynamic traffic distributions and rich environmental features. Inspired by the recent success of diffusion models in distribution modeling and Large Language Models (LLMs) in contextual understanding, we propose an LLM-Enhanced Spatio-temporal Diffusion Model (LSDM). LSDM integrates the generative power of diffusion models with the adaptive learning capabilities of transformers, augmented by the ability to capture multimodal environmental information for modeling service-level patterns and dynamics. Extensive evaluations on real-world service-level datasets demonstrate that the model excels in traffic usage predictions, showing outstanding generalization and adaptability. After incorporating contextual information via LLM, the performance improves by at least 2.83% in terms of the coefficient of determination. Compared to models of a similar type, such as CSDI, the root mean squared error can be reduced by at least 8.29%. The code and dataset will be available at: https://github.com/SoftYuaneR/LSDM.

Jierui Zhang, Jianhao Huang, Kaibin Huang

\emph{Integrated communication and computation} (IC$^2$) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC$^2$ technologies is hindered by the lack of a tractable theoretical framework for characterizing \emph{end-to-end} (E2E) inference performance. The metric is highly complicated as it needs to account for both channel distortion and artificial intelligence (AI) model architecture and computational complexity. In this work, we address this challenge by developing a tractable analytical model for E2E inference accuracy and leveraging it to design a \emph{channel-adaptive AI} algorithm that maximizes inference throughput, referred to as the edge processing rate (EPR), under latency and accuracy constraints. Specifically, we consider an edge inference system in which a server deploys a backbone model with early exit, which enables flexible computational complexity, to perform inference on data features transmitted by a mobile device. The proposed accuracy model characterizes high-dimensional feature distributions in the angular domain using a Mixture of von Mises (MvM) distribution. This leads to a desired closed-form expression for inference accuracy as a function of quantization bit-width and model traversal depth, which represents channel distortion and computational complexity, respectively. Building upon this accuracy model, we formulate and solve the EPR maximization problem under joint latency and accuracy constraints, leading to a channel-adaptive AI algorithm that achieves full IC$^2$ integration. The proposed algorithm jointly adapts transmit-side feature compression and receive-side model complexity according to channel conditions to maximize overall efficiency and inference throughput. Experimental results demonstrate its superior performance as compared with fixed-complexity counterparts.

Guanqiao Qu, Zheng Lin, Fangming Liu et al.

Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm called edge model caching. In this paper, we develop a novel model placement scheme, called parameter-sharing model caching (TrimCaching). TrimCaching exploits the key observation that a wide range of AI models, such as convolutional neural networks or large language models, can share a significant proportion of parameter blocks containing reusable knowledge, thereby improving storage efficiency. To this end, we formulate a parameter-sharing model placement problem to maximize the cache hit ratio in multi-edge wireless networks by balancing the fundamental tradeoff between storage efficiency and service latency. We show that the formulated problem is a submodular maximization problem with submodular constraints, for which no polynomial-time approximation algorithm exists. To overcome this challenge, we study an important special case, where a small fixed number of parameter blocks are shared across models, which often holds in practice. In such a case, a polynomial-time algorithm with $\left(1-ε\right)/2$-approximation guarantee is developed. Subsequently, we address the original problem for the general case by developing a greedy algorithm. Simulation results demonstrate that the proposed TrimCaching framework significantly improves the cache hit ratio compared with state-of-the-art content caching without exploiting shared parameters in AI models.

Adnan Shahid, Adrian Kliks, Ahmed Al-Tahmeesschi et al.

This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems. It highlights the development and deployment of Large Telecom Models (LTMs), which are tailored AI models designed to address the complex challenges faced by modern telecom networks. The paper covers a wide range of topics, from the architecture and deployment strategies of LTMs to their applications in network management, resource allocation, and optimization. It also explores the regulatory, ethical, and standardization considerations for LTMs, offering insights into their future integration into telecom infrastructure. The goal is to provide a comprehensive roadmap for the adoption of LTMs to enhance scalability, performance, and user-centric innovation in telecom networks.

Zhanwei Wang, Qunsong Zeng, Haotian Zheng et al.

One of the key missions of sixth-generation (6G) mobile networks is to deploy large-scale artificial intelligence (AI) models at the network edge to provide remote-inference services for edge devices. The resultant platform, known as edge inference, will support a wide range of Internet-of-Things applications, such as autonomous driving, industrial automation, and augmented reality. Given the mission-critical and time-sensitive nature of these tasks, it is essential to design edge inference systems that are both reliable and capable of meeting stringent end-to-end (E2E) latency constraints. Existing studies, which primarily focus on communication reliability as characterized by channel outage probability, may fail to guarantee E2E performance, specifically in terms of E2E inference accuracy and latency. To address this limitation, we propose a theoretical framework that introduces and mathematically characterizes the inference outage (InfOut) probability, which quantifies the likelihood that the E2E inference accuracy falls below a target threshold. Under an E2E latency constraint, this framework establishes a fundamental tradeoff between communication overhead (i.e., uploading more sensor observations) and inference reliability as quantified by the InfOut probability. To find a tractable way to optimize this tradeoff, we derive accurate surrogate functions for InfOut probability by applying a Gaussian approximation to the distribution of the received discriminant gain. Experimental results demonstrate the superiority of the proposed design over conventional communication-centric approaches in terms of E2E inference reliability.

Qian Chen, Xianhao Chen, Kaibin Huang

To bridge the digital divide, the space-ground integrated networks (SGINs), which will be a key component of the six-generation (6G) mobile networks, are expected to deliver artificial intelligence (AI) services to every corner of the world. One mission of SGINs is to support federated learning (FL) at a global scale. However, existing space-ground integrated FL frameworks involve ground stations or costly inter-satellite links, entailing excessive training latency and communication costs. To overcome these limitations, we propose an infrastructure-free federated learning framework based on a model dispersal (FedMeld) strategy, which exploits periodic movement patterns and store-carry-forward capabilities of satellites to enable parameter mixing across large-scale geographical regions. We theoretically show that FedMeld leads to global model convergence and quantify the effects of round interval and mixing ratio between adjacent areas on its learning performance. Based on the theoretical results, we formulate a joint optimization problem to design the staleness control and mixing ratio (SC-MR) for minimizing the training loss. By decomposing the problem into sequential SC and MR subproblems without compromising the optimality, we derive the round interval solution in a closed form and the mixing ratio in a semi-closed form to achieve the optimal latency-accuracy tradeoff. Experiments using various datasets demonstrate that FedMeld achieves superior model accuracy while significantly reducing communication costs as compared with traditional FL schemes for SGINs.

Zhonghao Lyu, Yulan Gao, Junting Chen et al.

Low-altitude economy (LAE) represents an emerging economic paradigm that redefines commercial and social aerial activities. Large artificial intelligence models (LAIMs) offer transformative potential to further enhance the intelligence of LAE services. However, deploying LAIMs in LAE poses several challenges, including the significant gap between their computational/storage demands and the limited onboard resources of LAE entities, the mismatch between lab-trained LAIMs and dynamic physical environments, and the inefficiencies of traditional decoupled designs for sensing, communication, and computation. To address these issues, we first propose a hierarchical system architecture tailored for LAIM deployment and present representative LAE application scenarios. Next, we explore key enabling techniques that facilitate the mutual co-evolution of LAIMs and low-altitude systems, and introduce a task-oriented execution pipeline for scalable and adaptive service delivery. Then, the proposed framework is validated through real-world case studies. Finally, we outline open challenges to inspire future research.

Huiling Yang, Zhanwei Wang, Kaibin Huang

Federated learning (FL) has emerged as a popular approach for collaborative machine learning in sixth-generation (6G) networks, primarily due to its privacy-preserving capabilities. The deployment of FL algorithms is expected to empower a wide range of Internet-of-Things (IoT) applications, e.g., autonomous driving, augmented reality, and healthcare. The mission-critical and time-sensitive nature of these applications necessitates the design of low-latency FL frameworks that guarantee high learning performance. In practice, achieving low-latency FL faces two challenges: the overhead of computing and transmitting high-dimensional model updates, and the heterogeneity in communication-and-computation (C$^2$) capabilities across devices. To address these challenges, we propose a novel C$^2$-aware framework for optimal batch-size control that minimizes end-to-end (E2E) learning latency while ensuring convergence. The framework is designed to balance a fundamental C$^2$ tradeoff as revealed through convergence analysis. Specifically, increasing batch sizes improves the accuracy of gradient estimation in FL and thus reduces the number of communication rounds required for convergence, but results in higher per-round latency, and vice versa. The associated problem of latency minimization is intractable; however, we solve it by designing an accurate and tractable surrogate for convergence speed, with parameters fitted to real data. This approach yields two batch-size control strategies tailored to scenarios with slow and fast fading, while also accommodating device heterogeneity. Extensive experiments using real datasets demonstrate that the proposed strategies outperform conventional batch-size adaptation schemes that do not consider the C$^2$ tradeoff or device heterogeneity.

Jianhao Huang, Qunsong Zeng, Kaibin Huang

Generative semantic communication (Gen-SemCom) with large artificial intelligence (AI) model promises a transformative paradigm for 6G networks, which reduces communication costs by transmitting low-dimensional prompts rather than raw data. However, purely prompt-driven generation loses fine-grained visual details. Additionally, there is a lack of systematic metrics to evaluate the performance of Gen-SemCom systems. To address these issues, we develop a hybrid Gen-SemCom system with a critical information embedding (CIE) framework, where both text prompts and semantically critical features are extracted for transmissions. First, a novel approach of semantic filtering is proposed to select and transmit the semantically critical features of images relevant to semantic label. By integrating the text prompt and critical features, the receiver reconstructs high-fidelity images using a diffusion-based generative model. Next, we propose the generative visual information fidelity (GVIF) metric to evaluate the visual quality of the generated image. By characterizing the statistical models of image features, the GVIF metric quantifies the mutual information between the distorted features and their original counterparts. By maximizing the GVIF metric, we design a channel-adaptive Gen-SemCom system that adaptively control the volume of features and compression rate according to the channel state. Experimental results validate the GVIF metric's sensitivity to visual fidelity, correlating with both the PSNR and critical information volume. In addition, the optimized system achieves superior performance over benchmarking schemes in terms of higher PSNR and lower FID scores.

Sijing Xie, Dingzhu Wen, Xiaonan Liu et al.

Federated Dropout is an efficient technique to overcome both communication and computation bottlenecks for deploying federated learning at the network edge. In each training round, an edge device only needs to update and transmit a sub-model, which is generated by the typical method of dropout in deep learning, and thus effectively reduces the per-round latency. \textcolor{blue}{However, the theoretical convergence analysis for Federated Dropout is still lacking in the literature, particularly regarding the quantitative influence of dropout rate on convergence}. To address this issue, by using the Taylor expansion method, we mathematically show that the gradient variance increases with a scaling factor of $γ/(1-γ)$, with $γ\in [0, θ)$ denoting the dropout rate and $θ$ being the maximum dropout rate ensuring the loss function reduction. Based on the above approximation, we provide the convergence analysis for Federated Dropout. Specifically, it is shown that a larger dropout rate of each device leads to a slower convergence rate. This provides a theoretical foundation for reducing the convergence latency by making a tradeoff between the per-round latency and the overall rounds till convergence. Moreover, a low-complexity algorithm is proposed to jointly optimize the dropout rate and the bandwidth allocation for minimizing the loss function in all rounds under a given per-round latency and limited network resources. Finally, numerical results are provided to verify the effectiveness of the proposed algorithm.

Feiran You, Hongyang Du, Kaibin Huang et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, leading to their increasing deployment in wireless networks for a wide variety of user services. However, the growing longer prompt setting highlights the crucial issue of computational resource demands and huge communication load. To address this challenge, we propose Joint Power and Prompt Optimization (JPPO), a framework that combines Small Language Model (SLM)-based prompt compression with wireless power allocation optimization. By deploying SLM at user devices for prompt compression and employing Deep Reinforcement Learning for joint optimization of compression ratio and transmission power, JPPO effectively balances service quality with resource efficiency. Experimental results demonstrate that our framework achieves high service fidelity and low bit error rates while optimizing power usage in wireless LLM services. The system reduces response time by about 17%, with the improvement varying based on the length of the original prompt.

Zhouxiang Zhao, Jiaxiang Wang, Zhaohui Yang et al.

The rapid development of agentic artificial intelligence (AI) is driving future wireless networks to evolve from passive data pipes into intelligent collaborative ecosystems under the emerging paradigm of integrated learning and communication (ILAC). However, realizing efficient agentic collaboration faces challenges not only in handling semantic redundancy but also in the lack of an integrated mechanism for communication, computation, and control. To address this, we propose a wireless agent network (WAN) framework that orchestrates a progressive knowledge aggregation mechanism. Specifically, we formulate the aggregation process as a joint energy minimization problem where the agents perform semantic compression to eliminate redundancy, optimize transmission power to deliver semantic payloads, and adjust physical trajectories to proactively enhance channel qualities. To solve this problem, we develop a hierarchical algorithm that integrates inner-level resource optimization with outer-level topology evolution. Theoretically, we reveal that incorporating a potential field into the topology evolution effectively overcomes the short-sightedness of greedy matching, providing a mathematically rigorous heuristic for long-term energy minimization. Simulation results demonstrate that the proposed framework achieves superior energy efficiency and scalability compared to conventional benchmarks, validating the efficacy of semantic-aware collaboration in dynamic environments.

You Zhou, Changsheng You, Kaibin Huang

Rare events, despite their infrequency, often carry critical information and require immediate attentions in mission-critical applications such as autonomous driving, healthcare, and industrial automation. The data-intensive nature of these tasks and their need for prompt responses, combined with designing edge AI (or edge inference), pose significant challenges in systems and techniques. Existing edge inference approaches often suffer from communication bottlenecks due to high-dimensional data transmission and fail to provide timely responses to rare events, limiting their effectiveness for mission-critical applications in the sixth-generation (6G) mobile networks. To overcome these challenges, we propose a channel-adaptive, event-triggered edge-inference framework that prioritizes efficient rare-event processing. Central to this framework is a dual-threshold, multi-exit architecture, which enables early local inference for rare events detected locally while offloading more complex rare events to edge servers for detailed classification. To further enhance the system's performance, we developed a channel-adaptive offloading policy paired with an online algorithm to dynamically determine the optimal confidence thresholds for controlling offloading decisions. The associated optimization problem is solved by reformulating the original non-convex function into an equivalent strongly convex one. Using deep neural network classifiers and real medical datasets, our experiments demonstrate that the proposed framework not only achieves superior rare-event classification accuracy, but also effectively reduces communication overhead, as opposed to existing edge-inference approaches.

Jierui Zhang, Jianhao Huang, Kaibin Huang

Federated learning (FL) has emerged as a widely adopted paradigm for enabling edge learning with distributed data while ensuring data privacy. However, the traditional FL with deep neural networks trained via backpropagation can hardly meet the low-latency learning requirements in the sixth generation (6G) mobile networks. This challenge mainly arises from the high-dimensional model parameters to be transmitted and the numerous rounds of communication required for convergence due to the inherent randomness of the training process. To address this issue, we adopt the state-of-the-art principle of maximal coding rate reduction to learn linear discriminative features and extend the resultant white-box neural network into FL, yielding the novel framework of Low-Latency Federated Learning (LoLaFL) via forward-only propagation. LoLaFL enables layer-wise transmissions and aggregation with significantly fewer communication rounds, thereby considerably reducing latency. Additionally, we propose two \emph{nonlinear} aggregation schemes for LoLaFL. The first scheme is based on the proof that the optimal NN parameter aggregation in LoLaFL should be harmonic-mean-like. The second scheme further exploits the low-rank structures of the features and transmits the low-rank-approximated covariance matrices of features to achieve additional latency reduction. Theoretic analysis and experiments are conducted to evaluate the performance of LoLaFL. In comparison with traditional FL, the two nonlinear aggregation schemes for LoLaFL can achieve reductions in latency of over 87\% and 97\%, respectively, while maintaining comparable accuracies.

Guanqiao Qu, Qian Chen, Xianhao Chen et al.

By provisioning inference offloading services, edge inference drives the rapid growth of AI applications at network edge. However, how to reduce the inference latency remains a significant challenge. To address this issue, we develop a parameter-sharing AI model loading (PartialLoading) framework for multi-user edge inference, which exploits two key insights: 1) the majority of latency arises from loading AI models into server GPU memory, and 2) different AI models can share a significant number of parameters, for which redundant loading should be avoided. Towards this end, we formulate a joint multi-user scheduling and spectrum bandwidth allocation problem to maximize task throughput by exploiting shared parameter blocks across models. The intuition is to judiciously schedule user requests to reuse the shared parameter blocks between consecutively loaded models, thereby reducing model loading time substantially. To facilitate solution finding, we decouple the problem into two sub-problems, i.e., user scheduling and bandwidth allocation, showing that solving them sequentially leads to the solution to the original problem. Due to the NP-hardness of the problem, we first study an important special case called the "backbone-sharing" case, and design a dynamic programming-based algorithm to obtain the optimal solution in polynomial time. For the general case, we propose a greedy heuristic to obtain the sub-optimal solution efficiently. Simulation results demonstrate that the proposed framework significantly improves task throughput under deadline constraints compared with user scheduling without exploiting parameter sharing.

Zhijie Cai, Xiaowen Cao, Xu Chen et al.

Recent breakthroughs in artificial intelligence (AI), wireless communications, and sensing technologies have accelerated the evolution of edge intelligence. However, conventional systems still grapple with issues such as low communication efficiency, redundant data acquisition, and poor model generalization. To overcome these challenges, we propose an innovative framework that enhances edge intelligence through AI-in-the-loop joint sensing and communication (JSAC). This framework features an AI-driven closed-loop control architecture that jointly optimizes system resources, thereby delivering superior system-level performance. A key contribution of our work is establishing an explicit relationship between validation loss and the system's tunable parameters. This insight enables dynamic reduction of the generalization error through AI-driven closed-loop control. Specifically, for sensing control, we introduce an adaptive data collection strategy based on gradient importance sampling, allowing edge devices to autonomously decide when to terminate data acquisition and how to allocate sample weights based on real-time model feedback. For communication control, drawing inspiration from stochastic gradient Langevin dynamics (SGLD), our joint optimization of transmission power and batch size converts channel and data noise into gradient perturbations that help mitigate overfitting. Experimental evaluations demonstrate that our framework reduces communication energy consumption by up to 77 percent and sensing costs measured by the number of collected samples by up to 52 percent while significantly improving model generalization -- with up to 58 percent reductions of the final validation loss. It validates that the proposed scheme can harvest the mutual benefit of AI and JSAC systems by incorporating the model itself into the control loop of the system.

Sijing Xie, Dingzhu Wen, Changsheng You et al.

Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training costs, this paper proposes Federated LoRA with Dropout (FedLoDrop), a new framework that applies dropout to the rows and columns of the trainable matrix in Federated LoRA. A generalization error bound and convergence analysis under sparsity regularization are obtained, which elucidate the fundamental trade-off between underfitting and overfitting. The error bound reveals that a higher dropout rate increases model sparsity, thereby lowering the upper bound of pointwise hypothesis stability (PHS). While this reduces the gap between empirical and generalization errors, it also incurs a higher empirical error, which, together with the gap, determines the overall generalization error. On the other hand, though dropout reduces communication costs, deploying FedLoDrop at the network edge still faces challenges due to limited network resources. To address this issue, an optimization problem is formulated to minimize the upper bound of the generalization error, by jointly optimizing the dropout rate and resource allocation subject to the latency and per-device energy consumption constraints. To solve this problem, a branch-and-bound (B\&B)-based method is proposed to obtain its globally optimal solution. Moreover, to reduce the high computational complexity of the B\&B-based method, a penalized successive convex approximation (P-SCA)-based algorithm is proposed to efficiently obtain its high-quality suboptimal solution. Finally, numerical results demonstrate the effectiveness of the proposed approach in mitigating overfitting and improving the generalization capability.

Xingkun Yin, Kaibin Huang, Dong In Kim et al.

Scaling model size, training data, and compute power have driven advances in large language models (LLMs), but these approaches are reaching saturation as human-generated text is exhausted and further gains diminish. We propose experience scaling, a framework for continuous post-deployment evolution for LLMs through autonomous interaction with the environment and collaborative sharing of accumulated experience. The framework captures raw interactions, distills them into compact, reusable knowledge, and periodically refines stored content to preserve relevance and efficiency. We validate the framework in simulated real-world scenarios involving generalization to previously unseen but related tasks, repetitive queries, and over-saturated knowledge stores. Across all settings, experience scaling improves accuracy, sustains performance over time, and maintains gains when applied to novel situations. These results demonstrate that structured post-deployment learning can extend LLM capabilities beyond the limits of static human-generated data, offering a scalable path for continued intelligence progress.

Jianhao Huang, Qunsong Zeng, Hongyang Du et al.

Semantic communication (SemCom) has emerged as a promising paradigm for achieving unprecedented communication efficiency in sixth-generation (6G) networks by leveraging artificial intelligence (AI) to extract and transmit the underlying meanings of source data. However, deploying SemCom over digital systems presents new challenges, particularly in ensuring robustness against transmission errors that may distort semantically critical content. To address this issue, this paper proposes a novel framework, termed generative feature imputing, which comprises three key techniques. First, we introduce a spatial error concentration packetization strategy that spatially concentrates feature distortions by encoding feature elements based on their channel mappings, a property crucial for both the effectiveness and reduced complexity of the subsequent techniques. Second, building on this strategy, we propose a generative feature imputing method that utilizes a diffusion model to efficiently reconstruct missing features caused by packet losses. Finally, we develop a semantic-aware power allocation scheme that enables unequal error protection by allocating transmission power according to the semantic importance of each packet. Experimental results demonstrate that the proposed framework outperforms conventional approaches, such as Deep Joint Source-Channel Coding (DJSCC) and JPEG2000, under block fading conditions, achieving higher semantic accuracy and lower Learned Perceptual Image Patch Similarity (LPIPS) scores.

Qian Chen, Xianhao Chen, Kaibin Huang

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant storage burden for an edge device. To address this challenge, we consider a scenario where experts are dispersed within an edge network for distributed inference. Based on the popular Top-$K$ expert selection strategy, we formulate a latency minimization problem by optimizing expert caching on edge servers under storage constraints. When $K=1$, the problem reduces to a monotone submodular maximization problem with knapsack constraints, for which we design a greedy-based algorithm with a $(1 - 1/e)$-approximation guarantee. For the general case where $K\geq1$, expert co-activation within the same MoE layer introduces non-submodularity, causing greedy methods to be ineffective. To tackle this issue, we propose a successive greedy decomposition method to decompose the original problem into a series of subproblems, with each being solved by a dynamic programming approach. Furthermore, we design an accelerated algorithm based on the max-convolution technique to obtain the approximate solution with a provable guarantee in polynomial time. Simulation results on various MoE models demonstrate that our method significantly reduces inference latency compared to existing baselines.

Zhanwei Wang, Kaibin Huang, Yonina C. Eldar

Federated Learning (FL) is a widely embraced paradigm for distilling artificial intelligence from distributed mobile data. However, the deployment of FL in mobile networks can be compromised by exposure to interference from neighboring cells or jammers. Existing interference mitigation techniques require multi-cell cooperation or at least interference channel state information, which is expensive in practice. On the other hand, power control that treats interference as noise may not be effective due to limited power budgets, and also that this mechanism can trigger countermeasures by interference sources. As a practical approach for protecting FL against interference, we propose Spectrum Breathing, which cascades stochastic-gradient pruning and spread spectrum to suppress interference without bandwidth expansion. The cost is higher learning latency by exploiting the graceful degradation of learning speed due to pruning. We synchronize the two operations such that their levels are controlled by the same parameter, Breathing Depth. To optimally control the parameter, we develop a martingale-based approach to convergence analysis of Over-the-Air FL with spectrum breathing, termed AirBreathing FL. We show a performance tradeoff between gradient-pruning and interference-induced error as regulated by the breathing depth. Given receive SIR and model size, the optimization of the tradeoff yields two schemes for controlling the breathing depth that can be either fixed or adaptive to channels and the learning process. As shown by experiments, in scenarios where traditional Over-the-Air FL fails to converge in the presence of strong interference, AirBreahing FL with either fixed or adaptive breathing depth can ensure convergence where the adaptive scheme achieves close-to-ideal performance.