Unified Deep Model Fixes the Pipeline Mismatch in OFDM Interference Cancellation

arXiv·low signal

Narrowband interference corrupts OFDM subcarriers and breaks classical soft demodulation. Conventional compressed-sensing mitigation has high sequential latency and leaves structured, non-Gaussian residuals, which cause log-likelihood ratio unreliability, decoder saturation, and severe error floors when a classical Gaussian demapper is applied downstream. This paper (arXiv 2607.08717, July 9) resolves the mismatch by learning cancellation and soft demodulation jointly rather than bolting a neural denoiser in front of a Gaussian assumption. The general lesson — that a learned stage feeding a hand-designed stage inherits the latter's distributional assumptions — generalizes well beyond wireless.