arXiv Machine Learning
Consistency Learning and Distillation for One-Step MIMO-OFDM Channel Estimation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 12
Null-Space Flow Matching for MIMO Channel Estimation in Latency-Constrained Systems
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 Machine Learning
Aug 7
EqDeepRx: Learning a Scalable and Interference Mitigating MIMO Receiver
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.
arXiv AI
Oct 28
JEPA-Inspired Latent Field Prediction for Sparse-Pilot MIMO-OFDM Channel Reconstruction
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.
arXiv AI
Oct 28
In-Context Learning for MIMO Turbo Receivers
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 Machine Learning
Jul 28
Restoration Flow Matching-Based Channel Refinement and Equalization Correction for MIMO Semantic Communications
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.
arXiv Machine Learning
Oct 8
SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation
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.