A Multi-Modal Foundational Model for Wireless Communication and Sensing
This addresses the problem of costly retraining and poor generalization for wireless communication and sensing systems, offering a foundational approach with potential broad impact in the field.
The paper tackles the lack of generalization in learning-based wireless techniques by introducing a task-agnostic, multi-modal foundational model that learns physics-aware representations, enabling robust adaptation to tasks like channel estimation and localization with reduced data needs and superior performance compared to baselines.
Artificial intelligence is a key enabler for next-generation wireless communication and sensing. Yet, today's learning-based wireless techniques do not generalize well: most models are task-specific, environment-dependent, and limited to narrow sensing modalities, requiring costly retraining when deployed in new scenarios. This work introduces a task-agnostic, multi-modal foundational model for physical-layer wireless systems that learns transferable, physics-aware representations across heterogeneous modalities, enabling robust generalization across tasks and environments. Our framework employs a physics-guided self-supervised pretraining strategy incorporating a dedicated physical token to capture cross-modal physical correspondences governed by electromagnetic propagation. The learned representations enable efficient adaptation to diverse downstream tasks, including massive multi-antenna optimization, wireless channel estimation, and device localization, using limited labeled data. Our extensive evaluations demonstrate superior generalization, robustness to deployment shifts, and reduced data requirements compared to task-specific baselines.