A hybrid transformer–zero-shot learning framework with Muon optimization for intelligent channel estimation in MIMO wireless systems
Wessam M Salama, Moustafa H Aly, Samah Alshathri, Walid El-Shafai · 2026
Read A hybrid transformer–zero-shot learning framework with Muon optimization for intelligent channel estimation in MIMO wireless systems by Wessam M Salama, Moustafa H Aly, Samah Alshathri, Walid El-Shafai (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13216647.txt.
Description
Wessam M. Salama and co-authors present a 2026 wireless engineering study on estimating the radio channel in MIMO systems. Many antennas talk at once there, and the channel must be measured before data can flow. Deep learning estimators usually need retraining whenever conditions change, which limits their use.
Their hybrid framework combines a Transformer network, zero-shot learning that maps channels into a shared attribute space, and the Muon optimizer. In simulations it beat classical least-squares and MMSE estimators and several deep learning baselines, especially in channel conditions never seen during training. Growing the array from 2 to 128 antennas at high signal quality cut estimation error by about 94 percent. The authors present the design as ready for next-generation networks.
Catalog record
| CREATOR | Wessam M Salama, Moustafa H Aly, Samah Alshathri, Walid El-Shafai |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 104 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |