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
arXiv:2506. 18295v2 Announce Type: replace-cross Abstract: Neural ray tracing (RT) has emerged as a promising paradigm for channel modeling by integrating physical propagation principles with neural networks.
By Kejia Bian, Meixia Tao, Shu Sun, Tongjia Zhang, Jun Yu
The paper proposes a CSI‑free hierarchical multi‑agent reinforcement learning framework for controlling reconfigurable reflective surfaces in millimeter‑wave networks. By replacing per‑element channel estimation with user localization data, the system uses a two‑tier neural architecture: a high‑level controller for discrete user‑to‑reflector assignments and low‑level controllers that optimize continuous focal points via MAPPO under a CTDE scheme. Deterministic ray‑tracing tests show RSSI gains of up to 7.79 dB over centralized PPO baselines and robust performance with sub‑meter localization errors for multiple users and reflector arrays.
By Hieu Le, Mostafa Ibrahim, Oguz Bedir, Jian Tao, Sabit Ekin
arXiv:2605.01777v2 Announce Type: replace-cross
Abstract: An evolution of Wireless Communications towards 5G and beyond provides improved user experience in terms of quality of services. Understandin...
By A. Sathi Babu, V. Udaya Sankar, Vishnu Ram OV
CSI-JEPA is a self‑supervised framework that learns reusable temporal‑spectral representations from unlabeled Wi‑Fi channel state information (CSI) by predicting latent features of masked channel regions. It tokenizes CSI along time and subcarrier dimensions and uses a channel‑variation‑aware masking strategy to focus on dynamic regions. After pretraining, the frozen encoder is adapted with lightweight adapters to a variety of downstream Wi‑Fi sensing tasks, achieving significant accuracy gains and label savings compared to supervised baselines.
By Xuanhao Luo, Zhizhen Li, Yuchen Liu
The paper presents a large‑scale, 3GPP TR 38.901‑compliant dataset for RIS‑aided millimeter‑wave B5G networks, covering 20 deployment variants with diverse user densities, fading, and blockage conditions. Each sample includes oracle RIS phase configurations from a brute‑force search, along with full CSI, per‑link channel decomposition, optimal phase matrices, and CQI labels, enabling a wide range of machine‑learning tasks. The authors also introduce a novel CSI‑to‑CQI mapping as a benchmark for scalable link‑quality prediction and evaluate it against state‑of‑the‑art models under various conditions.
By Pujitha Mamillapalli, Pankaj Singh Rathour, Abhinav Kumar
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. Existing wireless foundation models typically pretrain on channel tensors using masked reconstruction over subcarriers, antennas, or time but ignore the physical characteristics of wireless propagation.