The rapid evolution of wireless communication technologies, particularly massive multiple-input multiple-output (mMIMO) and millimeter-wave (mmWave), introduces significant network complexity and computational demands. Significant research efforts have been made to improve physical layer performance by resorting to deep learning (DL) methods, which, however, are usually task-specific and struggle with data scarcity and generalization. To address these challenges, we propose a novel In-Context Wireless Large Model (ICWLM), a wireless-native foundation model designed for simultaneous multi-task learning at the physical layer. Unlike conventional methods that adapt wireless data to pre-trained large language models (LLMs), ICWLM is trained directly on large-scale, mixed wireless datasets from scratch. It jointly solves multiple classical physical layer problems, including multi-user precoding (sum-rate maximization and max-min SINR) and channel prediction. A key innovation of ICWLM is its utilization of in-context learning (ICL), enabling the model to adapt to varying system configurations and channel conditions with minimal demonstration pairs, eliminating the need for extensive retraining. Extensive simulation results demonstrate that ICWLM achieves competitive performance compared to task-specific methods while exhibiting remarkable generalization capabilities to unseen system configurations. This work offers a promising paradigm for developing unified and adaptive AI models for future wireless networks, potentially reducing deployment complexity and enhancing intelligent resource management.
{"title":"ICWLM: A Multi-Task Wireless Large Model via In-Context Learning","authors":"Yuxuan Wen;Xiaoming Chen;Maojun Zhang;Zhaohui Yang;Chongwen Huang;Zhaoyang Zhang","doi":"10.1109/TCOMM.2026.3655778","DOIUrl":"10.1109/TCOMM.2026.3655778","url":null,"abstract":"The rapid evolution of wireless communication technologies, particularly massive multiple-input multiple-output (mMIMO) and millimeter-wave (mmWave), introduces significant network complexity and computational demands. Significant research efforts have been made to improve physical layer performance by resorting to deep learning (DL) methods, which, however, are usually task-specific and struggle with data scarcity and generalization. To address these challenges, we propose a novel In-Context Wireless Large Model (ICWLM), a wireless-native foundation model designed for simultaneous multi-task learning at the physical layer. Unlike conventional methods that adapt wireless data to pre-trained large language models (LLMs), ICWLM is trained directly on large-scale, mixed wireless datasets from scratch. It jointly solves multiple classical physical layer problems, including multi-user precoding (sum-rate maximization and max-min SINR) and channel prediction. A key innovation of ICWLM is its utilization of in-context learning (ICL), enabling the model to adapt to varying system configurations and channel conditions with minimal demonstration pairs, eliminating the need for extensive retraining. Extensive simulation results demonstrate that ICWLM achieves competitive performance compared to task-specific methods while exhibiting remarkable generalization capabilities to unseen system configurations. This work offers a promising paradigm for developing unified and adaptive AI models for future wireless networks, potentially reducing deployment complexity and enhancing intelligent resource management.","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"74 ","pages":"3646-3658"},"PeriodicalIF":8.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-19DOI: 10.1109/TCOMM.2026.3655763
Liangcheng Han;Haifan Yin;Robert W. Heath;Joseph Carlson
Traditional antenna arrays with a half-wavelength spacing between elements are capable of achieving a power gain proportional to the number of antennas $M$ . Superdirective antenna arrays, however, leverage smaller antenna spacing to approach an achievable power gain of $M^{2}$ , which could provide a significant performance improvement to the spectral efficiency in wireless communication systems. In this paper, we study the power scaling law of superdirective beamforming in multi-user communication systems using a uniform linear array (ULA). First, we extend superdirective precoding from single-user to multi-user multipath scenarios. Employing the basis of Legendre polynomials, we prove that the scaling laws of both the power gain and signal-to-interference-plus-noise ratio (SINR) are between $M$ and $M^{2}$ , where $M^{2}$ is achieved in the end-fire direction. To further enhance user power gains and effectively manage interference, we formulate and solve an optimization problem that maximizes the directivity gain while nullifying interference to other users. We demonstrate that this scheme can significantly improve spectral efficiency in multi-user settings, even when antenna spacing approaches zero. Moreover, we address the narrow directivity bandwidth issue, showing that the directivity of superdirective arrays decreases sharply as the frequency moves away from the center frequency, necessitating the use of multi-carrier technology to overcome this limitation. Simulation results verify the proposed power scaling law and show significant improvements in spectral efficiency with our proposed methods compared to a traditional antenna array with half-wavelength spacing.
{"title":"Power Scaling Law of Superdirective Multi-User Beamforming in Compact Arrays","authors":"Liangcheng Han;Haifan Yin;Robert W. Heath;Joseph Carlson","doi":"10.1109/TCOMM.2026.3655763","DOIUrl":"10.1109/TCOMM.2026.3655763","url":null,"abstract":"Traditional antenna arrays with a half-wavelength spacing between elements are capable of achieving a power gain proportional to the number of antennas <inline-formula> <tex-math>$M$ </tex-math></inline-formula>. Superdirective antenna arrays, however, leverage smaller antenna spacing to approach an achievable power gain of <inline-formula> <tex-math>$M^{2}$ </tex-math></inline-formula>, which could provide a significant performance improvement to the spectral efficiency in wireless communication systems. In this paper, we study the power scaling law of superdirective beamforming in multi-user communication systems using a uniform linear array (ULA). First, we extend superdirective precoding from single-user to multi-user multipath scenarios. Employing the basis of Legendre polynomials, we prove that the scaling laws of both the power gain and signal-to-interference-plus-noise ratio (SINR) are between <inline-formula> <tex-math>$M$ </tex-math></inline-formula> and <inline-formula> <tex-math>$M^{2}$ </tex-math></inline-formula>, where <inline-formula> <tex-math>$M^{2}$ </tex-math></inline-formula> is achieved in the end-fire direction. To further enhance user power gains and effectively manage interference, we formulate and solve an optimization problem that maximizes the directivity gain while nullifying interference to other users. We demonstrate that this scheme can significantly improve spectral efficiency in multi-user settings, even when antenna spacing approaches zero. Moreover, we address the narrow directivity bandwidth issue, showing that the directivity of superdirective arrays decreases sharply as the frequency moves away from the center frequency, necessitating the use of multi-carrier technology to overcome this limitation. Simulation results verify the proposed power scaling law and show significant improvements in spectral efficiency with our proposed methods compared to a traditional antenna array with half-wavelength spacing.","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"74 ","pages":"3659-3673"},"PeriodicalIF":8.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-19DOI: 10.1109/TCOMM.2026.3655757
Yuan Guo;Wen Chen;Qingqing Wu;Yang Liu;Qiong Wu
Integrated sensing and communication (ISAC) is a promising solution for the future sixth-generation (6G) system. However, classical fixed-position antenna (FPA) ISAC systems fail to fully utilize spatial degrees of freedom (DoFs), resulting in limited gains for both radar sensing and communication functionalities. This challenge can be addressed by the emerging novel fluid antenna (FA) technology, which can pursue better channel conditions and improve sensing and communication performances. In this paper, we aim to minimize the Cramér-Rao bound (CRB) for estimating the target’s angle while guaranteeing communication performance. This involves jointly optimizing active beamforming, power allocation, receiving filters, and FA position configurations, which is a highly non-convex problem. To tackle this difficulty, we propose an efficient iterative solution that analytically optimizes all variables without relying on numerical solvers, i.e., CVX. Specifically, by leveraging cutting-edge majorization-minimization (MM) and penalty-dual-decomposition (PDD) methods, we develop a low-complexity algorithm to solve the beamformer configuration problem containing the fractional and quartic terms. Numerical simulation results demonstrate the effectiveness and efficiency of our proposed algorithm, highlighting significant performance improvements achieved by employing FA in the ISAC system.
{"title":"Cramér-Rao Bound Optimization for Fluid Antenna-Empowered Integrated Sensing and Uplink Communication System","authors":"Yuan Guo;Wen Chen;Qingqing Wu;Yang Liu;Qiong Wu","doi":"10.1109/TCOMM.2026.3655757","DOIUrl":"10.1109/TCOMM.2026.3655757","url":null,"abstract":"Integrated sensing and communication (ISAC) is a promising solution for the future sixth-generation (6G) system. However, classical fixed-position antenna (FPA) ISAC systems fail to fully utilize spatial degrees of freedom (DoFs), resulting in limited gains for both radar sensing and communication functionalities. This challenge can be addressed by the emerging novel fluid antenna (FA) technology, which can pursue better channel conditions and improve sensing and communication performances. In this paper, we aim to minimize the Cramér-Rao bound (CRB) for estimating the target’s angle while guaranteeing communication performance. This involves jointly optimizing active beamforming, power allocation, receiving filters, and FA position configurations, which is a highly non-convex problem. To tackle this difficulty, we propose an efficient iterative solution that analytically optimizes all variables without relying on numerical solvers, i.e., CVX. Specifically, by leveraging cutting-edge majorization-minimization (MM) and penalty-dual-decomposition (PDD) methods, we develop a low-complexity algorithm to solve the beamformer configuration problem containing the fractional and quartic terms. Numerical simulation results demonstrate the effectiveness and efficiency of our proposed algorithm, highlighting significant performance improvements achieved by employing FA in the ISAC system.","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"74 ","pages":"3631-3645"},"PeriodicalIF":8.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-19DOI: 10.1109/TCOMM.2026.3655761
Binh-Minh Vu;Ngoc T. Dang;Sangmi Moon;Oh-Soon Shin;Van-Dinh Nguyen
This paper investigates the integration of active reconfigurable intelligent surfaces (ARISs) with uncrewed aerial vehicles (UAVs) in a mixed free-space optics radio frequency (FSO-RF) downlink communication system, enabling simultaneous lightwave information and power transfer (SLIPT). The proposed architecture addresses key challenges in UAV-based networks, including limited endurance and backhaul constraints, by allowing the UAV to harvest energy from the optical backhaul while transmitting RF signals enhanced via ARIS to ground users. The system design aims to maximize the minimum achievable rate among users by jointly optimizing the UAV’s beamforming strategy, 3D placement, ARIS reflection coefficients, optical ground station (OGS) transmit power and the power splitting (PS) ratio at the UAV. An alternating optimization framework is developed to decompose the resulting non-convex problem into efficiently solvable subproblems using inner approximation techniques. Simulation results confirm that the proposed approach significantly outperforms baseline schemes, such as passive RIS, fixed UAV deployment, and static PS configurations, delivering improved rate fairness and energy efficiency. These results demonstrate the potential of ARIS-assisted SLIPT-enabled UAVs to support robust and sustainable downlink communications in next-generation wireless networks.
{"title":"Optimizing Mixed FSO-RF Downlink Systems With Active RIS and SLIPT-Enabled UAV-BSs","authors":"Binh-Minh Vu;Ngoc T. Dang;Sangmi Moon;Oh-Soon Shin;Van-Dinh Nguyen","doi":"10.1109/TCOMM.2026.3655761","DOIUrl":"10.1109/TCOMM.2026.3655761","url":null,"abstract":"This paper investigates the integration of active reconfigurable intelligent surfaces (ARISs) with uncrewed aerial vehicles (UAVs) in a mixed free-space optics radio frequency (FSO-RF) downlink communication system, enabling simultaneous lightwave information and power transfer (SLIPT). The proposed architecture addresses key challenges in UAV-based networks, including limited endurance and backhaul constraints, by allowing the UAV to harvest energy from the optical backhaul while transmitting RF signals enhanced via ARIS to ground users. The system design aims to maximize the minimum achievable rate among users by jointly optimizing the UAV’s beamforming strategy, 3D placement, ARIS reflection coefficients, optical ground station (OGS) transmit power and the power splitting (PS) ratio at the UAV. An alternating optimization framework is developed to decompose the resulting non-convex problem into efficiently solvable subproblems using inner approximation techniques. Simulation results confirm that the proposed approach significantly outperforms baseline schemes, such as passive RIS, fixed UAV deployment, and static PS configurations, delivering improved rate fairness and energy efficiency. These results demonstrate the potential of ARIS-assisted SLIPT-enabled UAVs to support robust and sustainable downlink communications in next-generation wireless networks.","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"74 ","pages":"3600-3616"},"PeriodicalIF":8.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-19DOI: 10.1109/tcomm.2026.3655756
Bin Wang, Aiping Li, Xianchao Zhang, Jun Lu
{"title":"Compound Interference Recognition Method for UAV Communication Based on Multi-Modal Multi-Label Learning under Low INR","authors":"Bin Wang, Aiping Li, Xianchao Zhang, Jun Lu","doi":"10.1109/tcomm.2026.3655756","DOIUrl":"https://doi.org/10.1109/tcomm.2026.3655756","url":null,"abstract":"","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"139 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Base Station Sleeping Strategy for Large Scale Scenarios with Multi-Time-Window Spatio-Temporal Graph Convolutional Network","authors":"Mengke Yang, Daosen Zhai, Ruonan Zhang, Lei Liu, Zhiquan Liu, Dusit Niyato","doi":"10.1109/tcomm.2026.3655779","DOIUrl":"https://doi.org/10.1109/tcomm.2026.3655779","url":null,"abstract":"","PeriodicalId":13041,"journal":{"name":"IEEE Transactions on Communications","volume":"16 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：