A Wireless World Model for AI-Native 6G Networks
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_ | 1866917362877333504 |
|---|---|
| author | Chen, Ziqi Ren, Yi Huang, Yixuan Sun, Qi Li, Nan Huang, Yuhong I, Chih-Lin Li, Yifan Xia, Liang |
| author_facet | Chen, Ziqi Ren, Yi Huang, Yixuan Sun, Qi Li, Nan Huang, Yuhong I, Chih-Lin Li, Yifan Xia, Liang |
| contents | Integrating AI into the physical layer is a cornerstone of 6G networks. However, current data-driven approaches struggle to generalize across dynamic environments because they lack an intrinsic understanding of electromagnetic wave propagation. We introduce the Wireless World Model (WWM), a multi-modal foundation framework predicting the spatiotemporal evolution of wireless channels by internalizing the causal relationship between 3D geometry and signal dynamics. Pre-trained on a massive ray-traced multi-modal dataset, WWM overcomes the data authenticity gap, further validated under real-world measurement data. Using a joint-embedding predictive architecture with a multi-modal mixture-of-experts Transformer, WWM fuses channel state information, 3D point clouds, and user trajectories into a unified representation. Across the five key downstream tasks supported by WWM, it achieves remarkable performance in seen environments, unseen generalization scenarios, and real-world measurements, consistently outperforming SOTA uni-modal foundation models and task-specific models. This paves the way for physics-aware 6G intelligence that adapts to the physical world. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25216 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Wireless World Model for AI-Native 6G Networks Chen, Ziqi Ren, Yi Huang, Yixuan Sun, Qi Li, Nan Huang, Yuhong I, Chih-Lin Li, Yifan Xia, Liang Networking and Internet Architecture Artificial Intelligence Signal Processing Integrating AI into the physical layer is a cornerstone of 6G networks. However, current data-driven approaches struggle to generalize across dynamic environments because they lack an intrinsic understanding of electromagnetic wave propagation. We introduce the Wireless World Model (WWM), a multi-modal foundation framework predicting the spatiotemporal evolution of wireless channels by internalizing the causal relationship between 3D geometry and signal dynamics. Pre-trained on a massive ray-traced multi-modal dataset, WWM overcomes the data authenticity gap, further validated under real-world measurement data. Using a joint-embedding predictive architecture with a multi-modal mixture-of-experts Transformer, WWM fuses channel state information, 3D point clouds, and user trajectories into a unified representation. Across the five key downstream tasks supported by WWM, it achieves remarkable performance in seen environments, unseen generalization scenarios, and real-world measurements, consistently outperforming SOTA uni-modal foundation models and task-specific models. This paves the way for physics-aware 6G intelligence that adapts to the physical world. |
| title | A Wireless World Model for AI-Native 6G Networks |
| topic | Networking and Internet Architecture Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2603.25216 |