LWM-Spectro: A Foundation Model for Wireless Baseband Signal Spectrograms
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918286219804672 |
|---|---|
| author | Kim, Namhyun Alikhani, Sadjad Alkhateeb, Ahmed |
| author_facet | Kim, Namhyun Alikhani, Sadjad Alkhateeb, Ahmed |
| contents | The received in-phase and quadrature (I/Q) baseband signals inherently encode physical-layer and channel characteristics of wireless links. Learning robust and transferable representations directly from such raw signals, however, remains challenging due to heterogeneous communication systems, diverse propagation environments, and limited labeled data. To address this, we present LWM-Spectro, a transformer-based foundation model pretrained on large-scale I/Q data represented as time-frequency spectrograms. The model leverages self-supervised masked modeling, contrastive learning, and a mixture-of-experts (MoE) architecture to learn general-purpose wireless representations. These representations transfer effectively to downstream tasks such as modulation classification and joint SNR/mobility recognition, even with minimal supervision. Across tasks, LWM-Spectro consistently outperforms state-of-the-art deep learning baselines in both few-shot and data-rich regimes, providing a unified foundation for wireless learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08780 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LWM-Spectro: A Foundation Model for Wireless Baseband Signal Spectrograms Kim, Namhyun Alikhani, Sadjad Alkhateeb, Ahmed Information Theory Signal Processing The received in-phase and quadrature (I/Q) baseband signals inherently encode physical-layer and channel characteristics of wireless links. Learning robust and transferable representations directly from such raw signals, however, remains challenging due to heterogeneous communication systems, diverse propagation environments, and limited labeled data. To address this, we present LWM-Spectro, a transformer-based foundation model pretrained on large-scale I/Q data represented as time-frequency spectrograms. The model leverages self-supervised masked modeling, contrastive learning, and a mixture-of-experts (MoE) architecture to learn general-purpose wireless representations. These representations transfer effectively to downstream tasks such as modulation classification and joint SNR/mobility recognition, even with minimal supervision. Across tasks, LWM-Spectro consistently outperforms state-of-the-art deep learning baselines in both few-shot and data-rich regimes, providing a unified foundation for wireless learning. |
| title | LWM-Spectro: A Foundation Model for Wireless Baseband Signal Spectrograms |
| topic | Information Theory Signal Processing |
| url | https://arxiv.org/abs/2601.08780 |