# JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels

arXiv: https://arxiv.org/abs/2610.13315 · HTML: https://mlsanity.com/paper/2610.13315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Semantics-Empowered Communication for Networked Intelligent Systems](https://mlsanity.com/paper/2007.11579/) (2020)
- [WiFo: Wireless Foundation Model for Channel Prediction](https://mlsanity.com/paper/2412.08908/) (2024)
- [Variational Inference Aided Estimation of Time Varying Channels](https://mlsanity.com/paper/2210.17177/) (2022)
- [Reducing Pilots in Channel Estimation with Predictive Foundation Models](https://mlsanity.com/paper/2512.15562/) (2025)
- [Context-Aware Markov VAE for CSI Compression in Wireless Systems](https://mlsanity.com/paper/2606.16607/) (2026)

## Abstract (arXiv)

This paper considers channel state information (CSI) prediction using neural networks for time-varying multi-antenna channels from noisy historical observations. The main challenge is to exploit temporal correlation while distinguishing channel evolution from observation noise. We propose JEPA-kMMVAE, which combines a joint-embedding predictive architecture with a k-memory Markov variational autoencoder to predict future CSI through temporally structured latent representations. The framework supports direct prediction and residual corrections relative to the latest latent state and noisy CSI observation. Simulation results show that the residual configuration outperforms the evaluated baselines at moderate and high input CSI signal-to-noise ratios, while sequence baselines remain more accurate under stronger noise.