A Multi-Modal Foundational Model for Wireless Communication and Sensing
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911420923248640 |
|---|---|
| author | Yazdnian, Vahid Ghasempour, Yasaman |
| author_facet | Yazdnian, Vahid Ghasempour, Yasaman |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04016 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Multi-Modal Foundational Model for Wireless Communication and Sensing Yazdnian, Vahid Ghasempour, Yasaman Signal Processing Machine Learning 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. |
| title | A Multi-Modal Foundational Model for Wireless Communication and Sensing |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2602.04016 |