Loc X. Nguyen

Loc X. Nguyen, Huy Q. Le, Ye Lin Tun et al.

Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose training performance heavily relies on data availability. Existing studies often make unrealistic assumptions of a readily accessible data source, where in practice, data is mainly created on the client side. Due to privacy and security concerns, the transmission of data is restricted, which is necessary for conventional centralized training schemes. To address this challenge, we explore semantic communication in a federated learning (FL) setting that utilizes client data without leaking privacy. Additionally, we design our system to tackle the communication overhead by reducing the quantity of information delivered in each global round. In this way, we can save significant bandwidth for resource-limited devices and reduce overall network traffic. Finally, we introduce a mechanism to aggregate the global model from clients, called FedLol. Extensive simulation results demonstrate the effectiveness of our proposed technique compared to baseline methods.

Loc X. Nguyen, Avi Deb Raha, Huy Q. Le et al.

The sixth-generation wireless networks are envisioned to deliver ubiquitous, seamless, and intelligent connectivity that reaches far beyond the limits of terrestrial infrastructure. Non-terrestrial networks (NTNs) are central to this vision, extending coverage to underserved regions, remote terrain, and disaster zones that terrestrial deployment cannot economically reach. However, NTN architecture faces numerous limitations: severe path loss over long distances, long propagation delays, large and time-varying Doppler shifts, limited visibility windows, and tight on-board energy and computing budgets. Semantic communication (SemCom), which conveys the meaning of data rather than its raw bit-level representation, is unusually well matched to these conditions: extreme compression rate for task-oriented eases bandwidth scarcity, deep joint source-channel coding prevents the cliff effect due to low signal-to-noise ratio, and generative-AI reconstructs content from sparse cues that survive rain-faded or blocked links. This observation, that each NTN limitation maps onto a SemCom property that addresses it, motivates our survey. We first walk through the NTN limitations one by one, pairing each with the SemCom design choices that complement it, then we organize the literature along three axes: the NTN platform, the semantic methodology, and the supporting techniques, and follow this with platform-by-platform deep dives on satellite-centric, UAV/HAPS-centric, and integrated SAGIN systems. The survey concludes by identifying open research problems, gaps in existing standards, and future directions, including the application of foundation models, energy-aware scheduling, and quantum-assisted SemCom for deep space communication.

Huy Q. Le, Loc X. Nguyen, Yu Qiao et al.

Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data, making it ideal for privacy-sensitive applications. However, in real-world FL scenarios, clients often hold data from distinct domains, leading to severe domain shift and degraded global model performance. To address this, prototype learning has been emerged as a promising solution, which leverages class-wise feature representations. Yet, existing methods face two key limitations: (1) Existing prototype-based FL methods typically construct a $\textit{single global prototype}$ per class by aggregating local prototypes from all clients without preserving domain information. (2) Current feature-prototype alignment is $\textit{domain-agnostic}$, forcing clients to align with global prototypes regardless of domain origin. To address these challenges, we propose Federated Domain-Aware Prototypes (FedDAP) to construct domain-specific global prototypes by aggregating local client prototypes within the same domain using a similarity-weighted fusion mechanism. These global domain-specific prototypes are then used to guide local training by aligning local features with prototypes from the same domain, while encouraging separation from prototypes of different domains. This dual alignment enhances domain-specific learning at the local level and enables the global model to generalize across diverse domains. Finally, we conduct extensive experiments on three different datasets: DomainNet, Office-10, and PACS to demonstrate the effectiveness of our proposed framework to address the domain shift challenges. The code is available at https://github.com/quanghuy6997/FedDAP.

Loc X. Nguyen, Phuong-Nam Tran, Trung Thanh Pham et al.

Semantic communication (SemCom) is accelerating its momentum to catch up with the massive increase in users' demands in both quantity and quality, with the assistance of advanced deep learning (DL) techniques. Specifically, SemCom can actively embed the semantic meaning of the data into the transmission process, while eliminating statistical redundancy to preserve bandwidth resources for other users. Therefore, the transmitter encodes the message in the most concise way, while the receiver tries to interpret the message with the DL model and its knowledge of the transmitter's intended meaning. Most existing works only consider one transmitter and one receiver, which limits their ability to address the diversity in users' models and capabilities. Therefore, in this paper, we propose a multi-user semantic communication system where each user is equipped with a distinct DL-based joint source-channel decoder architecture, reflecting the diversity in computing capacity. The challenging issue with the proposed system is the catastrophic forgetting property of neural networks, where the DL-based encoder fails to encode the data for the previous user when being trained with a new user. To address this, we propose an anchor decoder with an architecture that is symmetric to the encoder. The symmetric decoder has the same computational capacity as the encoder, providing feedback that aligns with the encoder's extraction capabilities and enhances optimization efficiency. The parameters of the optimized encoder are then frozen and used to train decoders for various users, aligning them with the encoder outputs. Finally, we conduct a series of simulation experiments to validate the proposed framework against other benchmarks.

Loc X. Nguyen, Ji Su Yoon, Huy Q. Le et al.

The shift toward user-customized on-device learning places new demands on wireless systems: models must be trained on diverse, distributed data while meeting strict latency, bandwidth, and reliability constraints. To address this, we propose an Agentic AI as the control layer for managing federated learning (FL) over 6G networks, which translates high-level task goals into actions that are aware of network conditions. Rather than simply viewing FL as a learning challenge, our system sees it as a combined task of learning and network management. A set of specialized agents focused on retrieval, planning, coding, and evaluation utilizes monitoring tools and optimization methods to handle client selection, incentive structuring, scheduling, resource allocation, adaptive local training, and code generation. The use of closed-loop evaluation and memory allows the system to consistently refine its decisions, taking into account varying signal-to-noise ratios, bandwidth conditions, and device capabilities. Finally, our case study has demonstrated the effectiveness of the Agentic AI system's use of tools for achieving high performance.

Yu Qiao, Phuong-Nam Tran, Ji Su Yoon et al.

Reinforcement learning (RL)-based large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, have attracted widespread attention for their remarkable capabilities in multimodal data understanding. Meanwhile, the rapid expansion of information services has led to a growing demand for AI-enabled wireless networks. The open-source DeepSeek models are famous for their innovative designs, such as large-scale pure RL and cost-efficient training, which make them well-suited for practical deployment in wireless networks. By integrating DeepSeek-style LLMs with wireless infrastructures, a synergistic opportunity arises: the DeepSeek-style LLMs enhance network optimization with strong reasoning and decision-making abilities, while wireless infrastructure enables the broad deployment of these models. Motivated by this convergence, this survey presents a comprehensive DeepSeek-inspired exploration of RL-based LLMs in the context of wireless networks. We begin by reviewing key techniques behind network optimization to establish a foundation for understanding DeepSeek-style LLM integration. Next, we examine recent advancements in RL-based LLMs, using DeepSeek models as a representative example. Building on this, we explore the synergy between the two domains, highlighting motivations, challenges, and potential solutions. Finally, we highlight emerging directions for integrating LLMs with wireless networks, such as quantum, on-device, and neural-symbolic LLM models, as well as embodied AI agents. Overall, this survey offers a comprehensive examination of the interplay between DeepSeek-style LLMs and wireless networks, demonstrating how these domains can mutually enhance each other to drive innovation.

Yu Qiao, Huy Q. Le, Avi Deb Raha et al.

The rise of large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, has reshaped the artificial intelligence landscape. As prominent examples of foundational models (FMs) built on LLMs, these models exhibit remarkable capabilities in generating human-like content, bringing us closer to achieving artificial general intelligence (AGI). However, their large-scale nature, sensitivity to privacy concerns, and substantial computational demands present significant challenges to personalized customization for end users. To bridge this gap, this paper presents the vision of artificial personalized intelligence (API), focusing on adapting these powerful models to meet the specific needs and preferences of users while maintaining privacy and efficiency. Specifically, this paper proposes personalized federated intelligence (PFI), which integrates the privacy-preserving advantages of federated learning (FL) with the zero-shot generalization capabilities of FMs, enabling personalized, efficient, and privacy-protective deployment at the edge. We first review recent advances in both FL and FMs, and discuss the potential of leveraging FMs to enhance federated systems. We then present the key motivations behind realizing PFI and explore promising opportunities in this space, including efficient PFI, trustworthy PFI, and PFI empowered by retrieval-augmented generation (RAG). Finally, we outline key challenges and future research directions for deploying FM-powered FL systems at the edge with improved personalization, computational efficiency, and privacy guarantees. Overall, this survey aims to lay the groundwork for the development of API as a complement to AGI, with a particular focus on PFI as a key enabling technique.