# Recurrent Transformer-Based Near- and Far-Field THz Wideband Channel Estimation for UM-MIMO

arXiv: https://arxiv.org/abs/2605.12578 · HTML: https://mlsanity.com/paper/2605.12578/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 58 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [Block-Recurrent Transformers](https://mlsanity.com/paper/2203.07852/) (2022)
- [The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization](https://mlsanity.com/paper/2110.07732/) (2021)
- [Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling](https://mlsanity.com/paper/2303.11103/) (2023)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [Error Correction Code Transformer](https://mlsanity.com/paper/2203.14966/) (2022)
- [Uncovering Overfitting in Large Language Model Editing](https://mlsanity.com/paper/2410.07819/) (2024)
- [Channel Estimation and Hybrid Combining for Wideband Terahertz Massive MIMO Systems](https://mlsanity.com/paper/2102.06772/) (2021)
- [An Adaptive and Robust Deep Learning Framework for THz Ultra-Massive MIMO Channel Estimation](https://mlsanity.com/paper/2211.15939/) (2022)
- [Channel Estimation for Extremely Large-Scale Massive MIMO Systems](https://mlsanity.com/paper/1910.05432/) (2019)
- [Hybrid Beamforming for 5G and Beyond Millimeter-Wave Systems: A Holistic View](https://mlsanity.com/paper/1911.02853/) (2019)
- [Terahertz Integrated Sensing and Communication-Empowered UAVs in 6G: A Transceiver Design Perspective](https://mlsanity.com/paper/2502.04877/) (2025)
- [Hybrid Far- and Near-Field Channel Estimation for THz Ultra-Massive MIMO via Fixed Point Networks](https://mlsanity.com/paper/2205.04944/) (2022)
- [The Far-/Near-Field Beam Squint and Solutions for THz Intelligent Reflecting Surface Communications](https://mlsanity.com/paper/2208.12385/) (2022)
- [Near-Field Communications: What Will Be Different?](https://mlsanity.com/paper/2303.04003/) (2023)
- [Channel Estimation for XL-MIMO Systems with Polar-Domain Multi-Scale Residual Dense Network](https://mlsanity.com/paper/2308.16400/) (2023)
- [Mixed Attention Transformer Enhanced Channel Estimation for Extremely Large-Scale MIMO Systems](https://mlsanity.com/paper/2410.14439/) (2024)
- [Hybrid Beamforming for mm-Wave Massive MIMO Systems with Partially Connected RF Architecture](https://mlsanity.com/paper/2012.02889/) (2020)
- [Near-Field Channel Estimation for Extremely Large-Scale Array Communications: A model-based deep learning approach](https://mlsanity.com/paper/2211.15440/) (2022)
- [Parametric Near-Field Channel Estimation for Extremely Large Aperture Arrays](https://mlsanity.com/paper/2401.17693/) (2024)
- [Near-field Beam training for Extremely Large-scale MIMO Based on Deep Learning](https://mlsanity.com/paper/2406.03249/) (2024)

## Abstract (arXiv)

The integration of terahertz communications and ultra-massive multiple-input multiple-output (UM-MIMO) systems in 6G networks is motivated by their ability to enable unprecedented data rates, mitigate spectrum congestion, and enhance overall network performance. However, the enlarged antenna apertures and higher carrier frequencies in these systems increase the Rayleigh distance, causing users to span both the near-field and conventional far-field regions. Accurate spatial precoding thus requires exact channel estimation at the base station - a task made more challenging by the hybrid coexistence of near- and far-field effects and the limited number of digital chains available in hybrid beamforming architectures. In this paper, we propose a block recurrent transformer model to address this challenge. We demonstrate that a single transformer block equipped with state memory can be trained once and then iteratively applied for hybrid-field channel estimation. Furthermore, we train the model such that it generalizes to wireless channels with varying scatterer distances, different numbers of propagation paths, and wideband operation. Simulation results show that the proposed method achieves performance gains of approximately 5 dB and 7.5 dB in normalized mean squared error (NMSE) over state-of-the-art solutions in narrowband and wideband scenarios, respectively.