WirelessJEPA: A Multi-Antenna Foundation Model using Spatio-temporal Wireless Latent Predictions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911403928977408 |
|---|---|
| author | Chu, Viet Mashaal, Omar Abou-Zeid, Hatem |
| author_facet | Chu, Viet Mashaal, Omar Abou-Zeid, Hatem |
| contents | We propose WirelessJEPA, a novel wireless foundation model (WFM) that uses the Joint Embedding Predictive Architecture (JEPA). WirelessJEPA learns general-purpose representations directly from real-world multi-antenna IQ data by predicting latent representations of masked signal regions. This enables multiple diverse downstream tasks without reliance on carefully engineered contrastive augmentations. To adapt JEPA to wireless signals, we introduce a 2D antenna time representation that reshapes multi-antenna IQ streams into structured grids, allowing convolutional processing with block masking and efficient sparse computation over unmasked patches. Building on this representation, we propose novel spatio temporal mask geometries that encode inductive biases across antennas and time. We evaluate WirelessJEPA across six downstream tasks and demonstrate it's robust performance and strong task generalization. Our results establish that JEPA-based learning as a promising direction for building generalizable WFMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20190 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WirelessJEPA: A Multi-Antenna Foundation Model using Spatio-temporal Wireless Latent Predictions Chu, Viet Mashaal, Omar Abou-Zeid, Hatem Signal Processing We propose WirelessJEPA, a novel wireless foundation model (WFM) that uses the Joint Embedding Predictive Architecture (JEPA). WirelessJEPA learns general-purpose representations directly from real-world multi-antenna IQ data by predicting latent representations of masked signal regions. This enables multiple diverse downstream tasks without reliance on carefully engineered contrastive augmentations. To adapt JEPA to wireless signals, we introduce a 2D antenna time representation that reshapes multi-antenna IQ streams into structured grids, allowing convolutional processing with block masking and efficient sparse computation over unmasked patches. Building on this representation, we propose novel spatio temporal mask geometries that encode inductive biases across antennas and time. We evaluate WirelessJEPA across six downstream tasks and demonstrate it's robust performance and strong task generalization. Our results establish that JEPA-based learning as a promising direction for building generalizable WFMs. |
| title | WirelessJEPA: A Multi-Antenna Foundation Model using Spatio-temporal Wireless Latent Predictions |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2601.20190 |