arXiv:2604. 22005v2 Announce Type: replace-cross Abstract: Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems.
arXiv:2602. 11834v2 Announce Type: replace-cross Abstract: While machine learning (ML)-based receiver algorithms have received a great deal of attention in the recent literature, they often suffer from poor scaling with increasing spatial multiplexing order and lack of explainability and generalization.
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.
The paper introduces EXT-ICLNet, a Transformer-based detector for MIMO turbo receivers that uses pilots as in-context examples to learn the symbol extrinsic posterior distribution without explicit channel estimation. By implementing a log-domain prior skip connection, the network integrates seamlessly with existing turbo receivers, learning only extrinsic information. Numerical experiments on a 4×4 MIMO system with 16‑QAM and a quantized front end show that EXT-ICLNet outperforms baselines relying on explicit CSI estimation at low‑to‑medium SNRs and EP baselines with perfect CSI at high SNRs, as confirmed by EXIT chart comparisons.
arXiv:2607. 23615v1 Announce Type: new Abstract: In multiple-input multiple-output (MIMO) semantic communication, imperfect channel state information (CSI) and equalization mismatch can seriously degrade semantic reconstruction quality.
The paper introduces a diffusion-based channel estimation framework for MIMO systems that incorporates temporal dynamics via an LSTM-conditioned denoiser. It employs a learnable SNR-gated fusion mechanism to balance observation fidelity with generative priors across a wide SNR range, and uses DDIM-style reverse updates with SNR-adaptive truncation to reduce inference latency. Simulations on standardized time-evolving channel models show consistent performance gains over existing diffusion-based baselines while maintaining low latency.
arXiv:2509. 01641v3 Announce Type: replace-cross Abstract: We propose a novel diffusion model, termed the non-identical diffusion model, and investigate its application to wireless orthogonal frequency division multiplexing (OFDM) channel generation.
arXiv:2611.06432v1 Announce Type: cross Abstract: Reliable channel estimation and symbol detection in 5G New Radio (NR), as well as emerging 6G radio systems, rely on demodulation reference signals (...
The paper introduces a hybrid estimator for pilot‑limited MIMO channel estimation that frames the problem as low‑rank tensor completion from sparse pilot data. It compares Canonical Polyadic (CP) and Tucker decompositions, showing CP excels for specular channels while Tucker offers stability under extreme pilot scarcity. A lightweight 3D U‑Net is added to capture residual components, and the combined Tensor–NN approach achieves significant NMSE improvements over conventional methods across various pilot densities and channel models.
arXiv:2607. 27450v1 Announce Type: new Abstract: Accurate multipath parameter estimation is critical for modern wireless communication systems, particularly in challenging low-SNR environments.
arXiv:2506. 00452v5 Announce Type: replace-cross Abstract: In orthogonal frequency division multiplexing (OFDM), accurate channel estimation is crucial.
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.