Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization

2026-07-17

AI Summary

This work addresses the challenge of achieving both high accuracy and cross-scenario generalization in wireless localization within complex environments, where existing data-driven approaches suffer from heavy reliance on extensive labeled data and poor transferability. The authors propose SigMap, a multimodal foundation model that integrates wireless signals with 3D geospatial information. SigMap employs a periodic adaptive masking mechanism to learn robust representations and introduces a novel “map-as-prompt” framework, enabling efficient cross-scenario transfer through lightweight soft prompts. Evaluated across multiple localization tasks, the method achieves state-of-the-art performance and demonstrates significantly superior zero-shot generalization compared to current supervised and self-supervised approaches.

Abstract

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.

Problem

• wireless localization
• cross-scenario generalization
• foundation models
• environmental adaptation
• 5G/6G applications

Innovation

• foundation model
• wireless localization
• map-as-prompt
• cycle-adaptive masking
• cross-scenario generalization