WiNeRF is a neural field framework that learns a spatially continuous, complex-valued wireless channel representation from sparse channel state information collected by commodity WiFi devices. It incorporates system constraints such as antenna geometry, limited spatial resolution, and phase uncertainty through a 3D conical wave sampling model, a multi-resolution implicit scene representation, and a differentiable optimization framework. In diverse indoor environments with non‑line‑of‑sight regions, WiNeRF achieves a median prediction SNR of 5.3 dB, outperforming prior neural baselines by 4.9 dB on average, and produces a task‑agnostic channel representation that can be reused in standard signal‑processing pipelines without hardware or protocol changes.
By Saif Ur Rahman, Rafid Umayer Murshed, Anton Dmitriev, Cagri Tanriover, Rahul C. Shah, Elah\'e Soltanaghai
The paper introduces FAR-CSI, a structured time‑frequency representation that aligns historical uplink (UL) observations and future downlink (DL) predictions within a joint temporal and band positional field. By preserving distinct regions for UL context and DL targets, the method applies a unified routing rule across encoder, decoder, and target selection, maintaining consistent FDD geometry. Experiments show that FAR-CSI reduces NMSE by 21.44% compared to generic routing and improves CSI prediction accuracy and spectral efficiency across various mobility, horizon, data, and noise scenarios.
By Ning Yang, Yuming Xian, Tong Li, Ning Gao, Haijun Zhang
The paper introduces TRACE-CRC, a trajectory‑adaptive conformal risk control method for multi‑step channel state information (CSI) prediction. It builds Frobenius‑norm uncertainty balls around predicted CSI matrices and controls the risk that any future frame is uncovered, using future‑step‑dependent error profiling, trajectory difficulty stratification, and learn‑then‑test risk control. Experiments show that TRACE‑CRC delivers reliable trajectory‑level coverage with smaller uncertainty balls than conservative multi‑step corrections and avoids undercoverage seen in stepwise and adaptive baselines.
By Kiarash Rezaei, Mehdi Sattari, Javad Aliakbari, Tommy Svensson, Paolo Monti, Carlos Natalino
The paper introduces a JEPA-inspired latent field prediction model for reconstructing MIMO‑OFDM channels from sparse pilots. It maps observed CSI into latent time‑frequency tokens, predicts masked or future latent states using historical multi‑band context, and fuses these predictions with current noisy pilots to recover the full channel. Ray‑tracing experiments demonstrate that this approach reduces normalized mean square error compared to pilot‑only and direct reconstruction baselines.
By Yuzhi Yang, Brahim Mefgouda, Hang Zou, Lina Bariah, Anis Bara, Yuhuan Lu, Hao Zhang, Merouane Debbah
The paper introduces DRIFT, a lightweight framework for joint channel estimation and prediction in low Earth orbit non-terrestrial networks, aiming to reduce pilot overhead by using data-driven processing after the initial slot. DRIFT refines data-aided channel estimates and forecasts future channel responses with low computational cost, offering two variants based on convolutional and LSTM layers. Simulations show up to 12% spectral efficiency gain over conventional pilot-based systems, with under 200k multiply-accumulate operations suitable for on-board satellite implementation.
By Bruno De Filippo, Carla Amatetti, Alessandro Vanelli-Coralli
arXiv:2608. 05076v1 Announce Type: cross Abstract: Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam prediction, and localization based on wireless signals.
By Blessed Guda, Kayley Sze, Carlee Joe-Wong