Organizations: Research Institute for Digital Future, Khalifa University, 127788 Abu Dhabi, UAE · School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan · the Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, China
Accurate acquisition of full channel state information (CSI) is essential for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) wireless systems, while dense pilot-based estimation incurs substantial overhead. Directly minimizing the prediction error over raw CSI coefficients is fragile in realistic propagation environments, since small-scale fading, mobility, local scattering, and small spatial perturbations can induce large phase-sensitive variations. Nevertheless, wireless channels contain strong spatial, temporal, and frequency-domain correlations that can be more predictably represented in a latent propagation-field domain. Motivated by this observation, we propose a joint-embedding predictive architecture (JEPA)-inspired field world model, defined as a latent predictive model of the wireless propagation field, for sparse-pilot channel reconstruction. The model maps CSI observations into latent time-frequency tokens, predicts masked or future latent field states from historical multi-band context, and fuses the predicted latent prior with sparse noisy current pilots to reconstruct the full MIMO-OFDM channel. Ray-tracing experiments show that the proposed method improves normalized mean square error (NMSE) over pilot-only and direct reconstruction baselines, supporting latent field prediction as an effective prior for sparse-pilot channel acquisition.
Figures & tables
Fig. 1: Overview of the time-subband prediction JEPA pipeline.
Fig. 2: Pilot-aware channel prediction and reconstruction structure.
Fig. 3: The scenario considered for generating dataset based on the actual maps in Chicago within a range of around 1 km 2 . The red point indicates the BSs and blue lines are UE paths.
Item
Configuration
3.5 GHz subbands
3.1, 3.3, 3.5, 3.7, 3.9 GHz
3.5 GHz subcarrier spacing
480 kHz
28 GHz subbands
27, 28, 29 GHz
28 GHz subcarrier spacing
7.5 MHz
Subcarriers per subband
32
BS antennas
Two co-located 4×4 arrays
TABLE I: Dataset and system configuration.
Fig. 4: Pretraining results for the JEPA model.
Fig. 5: Downstream channel reconstruction performances of different methods. We note that the simple prediction experiment fails to converge.
Ericsson Research, Stockholm, Sweden · Department of Computer and Information Science, Linköping University, Linköping, Sweden · Department of Electrical Engineering, Linköping University, Linköping, Sweden
College of Electronic Information and Optical Engineering, Nankai University · School of Computing Science, University of Glasgow · School of Natural and Computing Science, University of Aberdeen