While machine learning is widely used to optimize wireless networks, training a separate model for each task in communication and localization is becoming increasingly unsustainable due to the significant costs associated with training and deployment. Foundation models offer a more scalable alternative by enabling a single model to be adapted across multiple tasks through fine-tuning with limited samples. However, current foundation models mostly rely on large-scale Transformer architectures, resulting in computationally intensive models unsuitable for deployment on typical edge devices. This paper presents a lightweight foundation model based on simple Multi-Layer-Perceptron (MLP) encoders that independently process input patches. Our model supports 4 types of downstream tasks (long-range technology recognition, short-range technology recognition, modulation recognition and line-of-sight-detection) from multiple input types (IQ and CIR) and different sampling rates. We show that, unlike Transformers, which can exhibit performance drops as downstream tasks are added, our MLP model maintains robust generalization performance, achieving over 97% accurate fine-tuning results for previously unseen data classes. These results are achieved despite having only 21K trainable parameters, allowing an inference time of 0.33 ms on common edge devices, making the model suitable for constrained real-time deployments.
Metasurfaces-Integrated Wireless Neural Networks for Lightweight Over-The-Air Edge Inference
Department of Informatics and Telecommunications, National and Kapodistrian University of Athens(信息与电信系,雅典国家与卡波迪斯蒂亚大学);National Inter-University Consortium for Telecommunications (CNIT)(电信国家大学联合体(CNIT));DIAG Department, Sapienza University of Rome(罗马萨皮恩扎大学DIAG系);DIET Department, Sapienza University of Rome(罗马萨皮恩扎大学DIET系)
Reading Radio from Camera: Visually-Grounded, Lightweight, and Interpretable RSSI Prediction
Khalifa University(哈利法大学);University of Electronic Science and Technology of China (UESTC)(电子科技大学);CNRS and Université de Lorraine, CRAN(法国国家科学研究中心和洛林大学,CRAN)
Adaptive Unequal Error Protection for Semantic Split Learning over Wireless Channels
University of Novi Sad(诺维萨德大学);Institute for Artificial Intelligence Research and Development of Serbia(塞尔维亚人工智能研发研究所);College of Electronic and Information Engineering, Tongji University(同济大学电子与信息工程学院)
A Photonic-Circuits-Inspired Compact Network: Toward Real-Time Wireless Signal Classification at the Edge
Princeton University(普林斯顿大学);Queen’s University(女王大学);Vector Institute(矢量研究所);Lockheed AI center(洛克希德人工智能中心);the Chinese University of Hong Kong(香港中文大学)
A Sensing Dataset Protocol for Benchmarking and Multi-Task Wireless Sensing
School of Information and Communication Engineering, Beijing University of Posts and Telecommunications(信息与通信工程学院,北京邮电大学);College of Electronics and Information Engineering, Shenzhen University(电子与信息工程学院,深圳大学);Huawei Technology Co. Ltd.(华为技术有限公司);Department of Electronic and Electrical Engineering, University College London(电子与电气工程系,伦敦大学学院)
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)
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)
Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection
Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, USA(弗吉尼亚大学电气与计算机工程系);Department of Computer Science, University of Virginia, USA(弗吉尼亚大学计算机科学系)
Conformal Calibration: Ensuring the Reliability of Black-Box AI in Wireless Systems
King’s Communications, Learning and Information Processing (KCLIP) lab(国王通讯、学习与信息处理实验室);Centre for Intelligent Information Processing Systems (CIIPS)(智能信息处理系统中心);Department of Engineering(工程系)