While wireless foundation models (FMs) are demonstrating strong potential to enable AI-Native 6G networks, their high computational cost remains a critical barrier to deployment. The large computational cost stems from the rigid, full-depth execution of the FM backbone for every task, a process we show is not only inefficient but can also degrade performance on unseen out-of-distribution (OOD) tasks. In this paper, we propose a novel early-exit FM framework that attaches lightweight, per-task heads, at the most appropriate exit-stage of a frozen wireless FM encoder, enabling variable-depth inference tailored to each task's preferred representation depth. Our results demonstrate that these intermediate-layer features not only speed-up inference significantly (up to 93% fewer FLOPs), but also provide more transferable representations that exceed the full encoder accuracy on unseen tasks. We further demonstrate that a simple fixed-exit strategy per task is more effective than traditional early-exiting policies that route different samples to different exits based on their perceived difficulty levels.
Foundation Models for Wireless Communications: From PHY Intelligence to Network Autonomy
Southeast University(东南大学);Purple Mountain Laboratories(紫金山实验室);Hong Kong University of Science and Technology(香港科技大学);Yonsei University(延世大学);MediaTek(联发科);Xi’an Jiaotong-Liverpool University(西交利物浦大学);Memorial University of Newfoundland(纽芬兰纪念大学);Imperial College(帝国理工学院)
WiFo-INR: A Wireless Foundation Model Based on Implicit Neural Representations
State Key Laboratory of Photonics and Communications, School of Electronics, Peking University(光电通信国家重点实验室,电子学院,北京大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization
Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Pengcheng Laboratory(鹏城实验室);Shanghai Academy of AI for Science(上海人工智能科学研究院);Artificial Intelligence Innovation and Incubation Institute, Fudan University(复旦大学人工智能创新与孵化院)
RA-LWLM: Retrieval-Augmented In-Context Localization with Wireless Foundation Models
Department of Electrical Engineering, Chalmers University of Technology(查尔姆斯理工大学电子工程系);Department of Electrical and Computer Engineering, Aarhus University(阿鲁斯大学电子与计算机工程系)
WiFo-MUD: Wireless Foundation Model for Heterogeneous Multi-User Demodulator
Peking University(北京大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Hong Kong University of Science and Technology(香港科技大学)
Large Wireless Localization Model (LWLM): A Foundation Model for Positioning in 6G Networks
Department of Electrical Engineering, Chalmers University of Technology(楚德大学电气工程系);School of Communication and Information Engineering, Shanghai University(上海大学通信与信息工程学院);Chalmers AI Research Center Consortium (CHAIR)(楚德人工智能研究中心联盟);National Academic Infrastructure for Supercomputing in Sweden (NAISS)(瑞典国家学术超级计算基础设施);SNS JU project 6G-DISAC under the EU’s Horizon Europe research and innovation Program(欧盟地平线欧洲研究与创新计划下的SNS JU项目6G-DISAC);Swedish Foundation for Strategic Research (SSF)(瑞典战略研究基金会);Chalmers Areas of Advance in ICT and Transport(楚德信息与交通领域先进领域)
Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models
National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications(中国移动网络技术国家工程研究中心,北京邮电大学);Department of Broadband Communication, Pengcheng Laboratory(宽带通信部,鹏城实验室);Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China(教育部民族语言智能分析与安全治理重点实验室,中央民族大学);China Telecom Corporation Limited Gansu Branch(中国电信集团甘肃分公司)
A Multi-Task Foundation Model for Wireless Channel Representation Using Contrastive and Masked Autoencoder Learning
Center for Pervasive Communications and Computing, University of California, Irvine(普及通信与计算中心,加州大学伊维特分校);Nokia Standards(诺基亚标准);Universitat Pompeu Fabra(庞培法布拉大学)
Foundation Models for Wireless Localization: Pretraining, Adaptation, and Utilization
Chalmers University of Technology(查尔姆斯理工大学);The Hong Kong University of Science and Technology(香港科技大学);Shenzhen University(深圳大学);Uppsala University(乌普萨拉大学);National Sun Yat-sen University(国立中山大学);Southeast University(东南大学)
A Unified Foundation Model for Wireless Technology Recognition and Localization
IDLab, Department of Information Technology, Ghent University - imec(根特大学-imec信息技术系IDLab);Center for 6G Technology, Khalifa University of Science and Technology(阿拉伯联合酋长国哈利法科学技术大学6G技术中心)
Hierarchical Wireless Foundation Model for Multi-Task Optimization
Department of Electrical and Electronic Engineering, Faculty of Engineering, Imperial College London(电气与电子工程系,工程学院,伦敦帝国理工学院);School of Mathematics and Statistics, Beijing Jiaotong University(数学与统计学学院,北京交通大学)
Channel2World: A Wireless Foundation Model for RF Environment Representation
School of Integrated Technology, Yonsei University(延世大学综合技术学院);School of Electrical and Electronic Engineering, Yonsei University(延世大学电气与电子工程学院);Department of Electrical and Computer Engineering, University of California, San Diego(加利福尼亚大学圣地亚哥分校电气与计算机工程系)
A Federated Fine-Tuning Paradigm of Foundation Models in Heterogenous Wireless Networks
Wireless AI System Research Team, China Telecom Research Institute(中国电信研究院无线AI系统研究团队);The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications(北京邮电大学网络与交换技术国家重点实验室);Singapore University of Technology and Design(新加坡科技设计大学)
Wireless AI Evolution: From Statistical Learners to Electromagnetic-Guided Foundation Models
Central China Normal University(华中师范大学);Information Support Force Engineering University(信息支援工程大学);National University of Defense Technology(国防科技大学);Henan Polytechnic University(河南理工大学);Tsinghua University(清华大学);Nanyang Technological University(南洋理工大学)
A Foundation Model for Large-Scale Wireless Network Planning , Operation and Optimization
Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Sun Yat-Sen University, Shenzhen(中山大学(深圳));Shenzhen Loop Area Institute(深圳河套学院)