发表机构
Harbin Institute of Technology, Shenzhen; Pengcheng Laboratory; Shanghai Academy of AI for Science; Artificial Intelligence Innovation and Incubation Institute, Fudan University（哈尔滨工业大学（深圳）; 鹏城实验室; 上海人工智能科学研究院; 复旦大学人工智能创新与孵化院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无线定位在不同环境中面临的挑战及现有方法的局限，提出多模态基础模型SigMap，通过循环自适应掩码策略和“地图即提示”框架学习无线表示并实现跨场景适应，实验证明其性能领先且零样本泛化能力强。
AI 中文摘要
准确且稳健的无线定位是新兴5G/6G应用（如自动驾驶、扩展现实和智能制造）的关键推动因素。尽管其很重要，但由于无线信号的复杂性及其对环境变化的敏感性，在不同环境中实现精确的定位仍然具有挑战性。现有的数据驱动方法通常泛化能力有限，需要大量标记数据且难以适应新场景。为解决这些限制，我们提出了SigMap，这是一种多模态基础模型，引入了两个关键创新：（1）一种循环自适应掩码策略，基于信道周期性特征动态调整掩码模式以学习稳健的无线表示；（2）一种新颖的“地图即提示”框架，通过轻量级软提示集成3D地理信息以实现有效的跨场景适应。大量实验表明，我们的模型在多个定位任务中实现了领先的性能，在未见环境中展现出强大的零样本泛化能力，显著优于有监督和自监督的基线。
英文摘要
Accurate and robust wireless localization is a critical enabler for emerging 5G/6G applications, including autonomous driving, extended reality, and smart manufacturing. Despite its importance, achieving precise localization across diverse environments remains challenging due to the complex nature of wireless signals and their sensitivity to environmental changes. Existing data-driven approaches often suffer from limited generalization capability, requiring extensive labeled data and struggling to adapt to new scenarios. To address these limitations, we propose SigMap, a multimodal foundation model that introduces two key innovations: (1) A cycle-adaptive masking strategy that dynamically adjusts masking patterns based on channel periodicity characteristics to learn robust wireless representations; (2) A novel "map-as-prompt" framework that integrates 3D geographic information through lightweight soft prompts for effective cross-scenario adaptation. Extensive experiments demonstrate that our model achieves state-of-the-art performance across multiple localization tasks while exhibiting strong zero-shot generalization in unseen environments, significantly outperforming both supervised and self-supervised baselines by considerable margins.
Comments17pages, 9 figures, poster in International Conference on Learning Representations (ICLR), 2026
