# Deep Learning-Based Tri-Hybrid Multi-User MIMO Precoding: The Blessing of EM-Reconfigurable Antennas

arXiv: https://arxiv.org/abs/2609.39167 · HTML: https://mlsanity.com/paper/2609.39167/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [A Tutorial on Extremely Large-Scale MIMO for 6G: Fundamentals, Signal Processing, and Applications](https://mlsanity.com/paper/2307.07340/) (2023)
- [Fluid Antenna Systems](https://mlsanity.com/paper/2005.11561/) (2020)
- [Data-Driven Deep Learning Based Hybrid Beamforming for Aerial Massive MIMO-OFDM Systems with Implicit CSI](https://mlsanity.com/paper/2201.06778/) (2022)
- [Principal Component Analysis Based Broadband Hybrid Precoding for Millimeter-Wave Massive MIMO Systems](https://mlsanity.com/paper/1903.09074/) (2019)
- [Rotatable Antenna-Enabled Wireless Communication: Modeling and Optimization](https://mlsanity.com/paper/2501.02595/) (2025)
- [Radiation Pattern Reconfigurable FAS-Empowered Interference-Resilient UAV Communication](https://mlsanity.com/paper/2510.00581/) (2025)
- [Reconfigurable Massive MIMO: Harnessing the Power of the Electromagnetic Domain for Enhanced Information Transfer](https://mlsanity.com/paper/2302.11385/) (2023)
- [Reconfigurable Massive MIMO: Precoding Design and Channel Estimation in the Electromagnetic Domain](https://mlsanity.com/paper/2405.02823/) (2024)
- [Embracing Reconfigurable Antennas in the Tri-hybrid MIMO Architecture for 6G and Beyond](https://mlsanity.com/paper/2501.16610/) (2025)
- [Electromagnetically Reconfigurable Fluid Antenna System for Wireless Communications: Design, Modeling, Algorithm, Fabrication, and Experiment](https://mlsanity.com/paper/2502.19643/) (2025)
- [REMAA: Reconfigurable Pixel Antenna-based Electronic Movable-Antenna Arrays for Multiuser Communications](https://mlsanity.com/paper/2504.00787/) (2025)
- [Design and Channel Modeling of Electromagnetically Reconfigurable Antennas](https://mlsanity.com/paper/2505.02251/) (2025)
- [Tri-Hybrid Multi-User Precoding Based on Electromagnetically Reconfigurable Antennas](https://mlsanity.com/paper/2505.02254/) (2025)
- [Tri-Hybrid Beamforming for Radiation-Center Reconfigurable Antenna Array: Spectral Efficiency and Energy Efficiency](https://mlsanity.com/paper/2508.15924/) (2025)
- [AI Signal Processing Paradigm for Movable Antenna: From Spatial Position Optimization to Electromagnetic Reconfigurability](https://mlsanity.com/paper/2510.19209/) (2025)
- [Antenna Coding Design for Multi-User Transmissions Using Pixel Antennas](https://mlsanity.com/paper/2512.10246/) (2025)
- [Movable Antenna for Integrating Near-field Channel Estimation and Localization](https://mlsanity.com/paper/2601.08357/) (2026)
- [Transformer-based Hybrid Beamforming with Dynamic Subarray for Near-Space Airship-Borne Communications](https://mlsanity.com/paper/2602.07509/) (2026)
- [Tri-Domain Multiuser MIMO Precoding Optimization and Channel Estimation with Spatial-EM Reconfigurable Antenna](https://mlsanity.com/paper/2605.23682/) (2026)

## Abstract (arXiv)

Electromagnetic (EM)-reconfigurable antennas provide multiple candidate radiation patterns per element, thereby introducing an additional EM-domain degree of freedom. Integrating radiation-pattern reconfigurability, realized as EM-domain precoding, with conventional hybrid analog-digital precoding yields tri-hybrid multiple-input multiple-output (MIMO) precoding, which can substantially improve the spectral efficiency of wideband multi-user MIMO orthogonal frequency-division multiplexing (OFDM) systems. However, the joint design of EM, analog, and digital precoding remains challenging. To address this challenge, we propose a tri-hybrid precoding network (Tri-PNet) based on Conformer, an emerging neural architecture that combines the local modeling strength of convolutional neural networks with the global dependency modeling of Transformers. Furthermore, two representative radiation-pattern modes, i.e., the non-regular mode and the 3rd Generation Partnership Project (3GPP) Technical Report (TR) 38.901 mode, are investigated. Tri-PNet is trained in an unsupervised manner to jointly learn EM, analog, and digital precoding by maximizing the average sum spectral efficiency. Its radiation-pattern selection network (RPSNet) employs a Conformer encoder to capture both local and global frequency-domain correlations, whereas its hybrid analog-digital precoding network (HPNet) combines cross-attention and dual-path processing with singular-value-decomposition (SVD) and zero-forcing (ZF) priors. Simulation results under both radiation-pattern modes demonstrate that Tri-PNet outperforms random EM precoding and conventional hybrid MIMO without EM precoding, approaches the greedy EM precoding search scheme with substantially lower online complexity, and remains robust to imperfect channel state information (CSI).