# A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff

arXiv: https://arxiv.org/abs/2507.18587 · HTML: https://mlsanity.com/paper/2507.18587/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [Unsupervised Deep Learning for Massive MIMO Hybrid Beamforming](https://mlsanity.com/paper/2007.00038/) (2020)
- [BERT4MIMO: A Foundation Model using BERT Architecture for Massive MIMO Channel State Information Prediction](https://mlsanity.com/paper/2501.01802/) (2025)
- [A Deep Learning-Based Framework for Low Complexity Multi-User MIMO Precoding Design](https://mlsanity.com/paper/2207.03765/) (2022)
- [SAGE-HB: Swift Adaptation and Generalization in Massive MIMO Hybrid Beamforming](https://mlsanity.com/paper/2401.10513/) (2024)
- [Learning Energy-Efficient Hardware Configurations for Massive MIMO Beamforming](https://mlsanity.com/paper/2308.06376/) (2023)

## Built on by (most cited first, 1 of 1)

- [Wireless Foundation Models: State-of-the-Art and Open Challenges](https://mlsanity.com/paper/2609.04707/) (2026)

## Abstract (arXiv)

Deep learning (DL) has emerged as a solution for precoding in massive multiple-input multiple-output (mMIMO) systems due to its capacity to learn the characteristics of the propagation environment. However, training such a model requires high-quality, local datasets at the deployment site, which are often difficult to collect. We propose a transformer-based foundation model for mMIMO precoding that seeks to minimize the energy consumption of the transmitter while dynamically adapting to per-user rate requirements. At equal energy consumption, zero-shot deployment of the proposed foundation model significantly outperforms zero forcing, and approaches weighted minimum mean squared error performance with 8x less complexity. To address model adaptation in data-scarce settings, we introduce a data augmentation method that finds training samples similar to the target distribution by computing the cosine similarity between the outputs of the pre-trained feature extractor. Our work enables the implementation of DL-based solutions in practice by addressing challenges of data availability and training complexity. Moreover, the ability to dynamically configure per-user rate requirements can be leveraged by higher level resource allocation and scheduling algorithms for greater control over energy efficiency, spectral efficiency and fairness.