# Learning Latent Wireless Dynamics from Channel State Information

arXiv: https://arxiv.org/abs/2409.10045 · HTML: https://mlsanity.com/paper/2409.10045/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [A-JEPA: Joint-Embedding Predictive Architecture Can Listen](https://mlsanity.com/paper/2311.15830/) (2023)
- [Channel Charting: Locating Users within the Radio Environment using Channel State Information](https://mlsanity.com/paper/1807.05247/) (2018)
- [Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud](https://mlsanity.com/paper/2404.16432/) (2024)
- [Angle-Delay Profile-Based and Timestamp-Aided Dissimilarity Metrics for Channel Charting](https://mlsanity.com/paper/2308.09539/) (2023)
- [Wireless Channel Charting: Theory, Practice, and Applications](https://mlsanity.com/paper/2304.08095/) (2023)
- [Time-Series JEPA for Predictive Remote Control under Capacity-Limited Networks](https://mlsanity.com/paper/2406.04853/) (2024)
- [Velocity-Based Channel Charting with Spatial Distribution Map Matching](https://mlsanity.com/paper/2311.08016/) (2023)

## Built on by (most cited first, 7 of 7)

- [Structured Latent Dynamics in Wireless CSI via Homomorphic World Models](https://mlsanity.com/paper/2603.20048/) (2026)
- [CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision](https://mlsanity.com/paper/2605.14171/) (2026)
- [Semantic Communication meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence](https://mlsanity.com/paper/2505.20964/) (2025)
- [From Pixels to CSI: Distilling Latent Dynamics For Efficient Wireless Resource Management](https://mlsanity.com/paper/2506.16216/) (2025)
- [Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method](https://mlsanity.com/paper/2607.09078/) (2026)
- [Chartwin: a Case Study on Channel Charting-aided Localization in Dynamic Digital Network Twins](https://mlsanity.com/paper/2508.09055/) (2025)
- [RAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control](https://mlsanity.com/paper/2610.17584/) (2026)

## Abstract (arXiv)

In this work, we propose a novel data-driven machine learning (ML) technique to model and predict the dynamics of the wireless propagation environment in latent space. Leveraging the idea of channel charting, which learns compressed representations of high-dimensional channel state information (CSI), we incorporate a predictive component to capture the dynamics of the wireless system. Hence, we jointly learn a channel encoder that maps the estimated CSI to an appropriate latent space, and a predictor that models the relationships between such representations. Accordingly, our problem boils down to training a joint-embedding predictive architecture (JEPA) that simulates the latent dynamics of a wireless network from CSI. We present numerical evaluations on measured data and show that the proposed JEPA displays a two-fold increase in accuracy over benchmarks, for longer look-ahead prediction tasks.