AI RESEARCH
Score Based Error Correcting Code Decoder
arXiv CS.AI
•
ArXi:2605.28358v1 Announce Type: cross Error-correcting codes enable reliable communication, yet practical soft decoding remains challenging across code families and block lengths. We propose SB-ECC, a score-based decoder that casts decoding as continuous-time denoising. A neural denoiser defines a probability-flow ordinary differential equation (ODE) that iteratively updates the noisy channel observation toward a valid codeword, guided by parity constraints.