# Site-Specific MIMO Channel Generation via Diffusion and Flow Matching: Fidelity, Efficiency, and Downstream Utility

arXiv: https://arxiv.org/abs/2606.20098 · HTML: https://mlsanity.com/paper/2606.20098/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models.
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- Diffusion models / [Diffusion for compression and wireless](https://mlsanity.com/diffusion/diffusion-for-compression-and-wireless/)

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Multi-resolution CSI Feedback with deep learning in Massive MIMO System](https://mlsanity.com/paper/1910.14322/) (2019)
- [Approximating the Void: Learning Stochastic Channel Models from Observation with Variational Generative Adversarial Networks](https://mlsanity.com/paper/1805.06350/) (2018)
- [Generative Diffusion Models for Radio Wireless Channel Modelling and Sampling](https://mlsanity.com/paper/2308.05583/) (2023)
- [Generating High Dimensional User-Specific Wireless Channels using Diffusion Models](https://mlsanity.com/paper/2409.03924/) (2024)
- [Generative Neural Network Channel Modeling for Millimeter-Wave UAV Communication](https://mlsanity.com/paper/2012.09133/) (2020)
- [MIMO-GAN: Generative MIMO Channel Modeling](https://mlsanity.com/paper/2203.08588/) (2022)
- [Evaluation Metrics and Methods for Generative Models in the Wireless PHY Layer](https://mlsanity.com/paper/2408.00634/) (2024)
- [Grid-Free MIMO Beam Alignment through Site-Specific Deep Learning](https://mlsanity.com/paper/2209.08198/) (2022)
- [GAN-based Massive MIMO Channel Model Trained on Measured Data](https://mlsanity.com/paper/2403.05321/) (2024)
- [Transformer-Based Neural Surrogate for Link-Level Path Loss Prediction from Variable-Sized Maps](https://mlsanity.com/paper/2310.04570/) (2023)
- [Spatially Consistent Air-to-Ground Channel Modeling via Generative Neural Networks](https://mlsanity.com/paper/2402.03517/) (2024)
- [Generative Diffusion Model-based Compression of MIMO CSI](https://mlsanity.com/paper/2503.03753/) (2025)
- [Deep Learning based Modeling of Wireless Communication Channel with Fading](https://mlsanity.com/paper/2312.06849/) (2023)
- [Channel Modeling for FR3 Upper Mid-band via Generative Adversarial Networks](https://mlsanity.com/paper/2404.17069/) (2024)
- [Channel Geometry Preserving Generative Models for CSI Feedback in MU-MIMO](https://mlsanity.com/paper/2605.08628/) (2026)

## Abstract (arXiv)

This paper explores the use of generative models to synthesize high-quality, site-specific multiple-input multiple-output (MIMO) channel data, addressing the high cost of the extensive measurement campaigns required to acquire real-world data for AI-native wireless networks. Two location-conditioned generative paradigms are compared: a conditional denoising diffusion implicit model (cDDIM), and a conditional flow matching model (cFMM). Both these models generate MIMO channel matrices conditioned on user coordinates, to preserve the spatial structure of the deployment site. The approaches are evaluated across three dimensions: statistical fidelity (including beam consistency and effective rank), generation efficiency, and utility in downstream tasks such as channel-state information compression and beam alignment. Results across diverse propagation scenarios (28 GHz and 3.5 GHz, both line-of-sight and non-line-of-sight) demonstrate that both models accurately capture site-specific characteristics, even when trained on scarce ground-truth data. Notably, cFMM achieves a quality comparable to cDDIM with roughly an order of magnitude less inference time. Augmenting scarce site-specific datasets with these synthetic channels yields hefty performance gains in downstream physical layer tasks compared to using scarce data alone or stochastic channels.