# Context-Aware Markov VAE for CSI Compression in Wireless Systems

arXiv: https://arxiv.org/abs/2606.16607 · HTML: https://mlsanity.com/paper/2606.16607/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 4 of 4)

- [Multi-resolution CSI Feedback with deep learning in Massive MIMO System](https://mlsanity.com/paper/1910.14322/) (2019)
- [Distributed Deep Convolutional Compression for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2003.04684/) (2020)
- [Variational Inference Aided Estimation of Time Varying Channels](https://mlsanity.com/paper/2210.17177/) (2022)
- [An Adaptive CSI Feedback Model Based on BiLSTM for Massive MIMO-OFDM Systems](https://mlsanity.com/paper/2408.06359/) (2024)

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

- [JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels](https://mlsanity.com/paper/2610.13315/) (2026)

## Abstract (arXiv)

This paper considers neural channel state information (CSI) compression for time-varying massive multiple-input multiple-output (MIMO) channels in frequency division duplex (FDD) systems with limited feedback resources. The main challenge lies in obtaining a compact and efficient representation of the CSI given that it exhibits strong temporal correlation across successive snapshots. Existing memoryless compression models do not exploit this property, while simple temporal extensions often incorporate multiple observations without explicitly modeling the latent dynamics. We propose a context-aware compression framework based on a k-memory Markov variational autoencoder (k-MMVAE), which uses a finite temporal window to capture the evolution of CSI in the latent space. The model introduces Markov-structured latent dynamics with finite memory, enabling efficient use of temporal dependencies for compression. Simulation results show that the proposed approach improves target CSI reconstruction performance compared to memoryless and weakly sequential baselines, particularly at low and moderate compression rates. These results suggest that explicit latent temporal modeling can provide an effective mechanism for CSI compression under limited feedback constraints.