AI RESEARCH
Contextual Memory-Enhanced Source Coding for Low-SNR Communications
arXiv CS.LG
•
ArXi:2605.04400v1 Announce Type: cross While Separate Source-Channel Coding (SSCC) retains the practical benefits of modular system design, its effectiveness in noisy text transmission is fundamentally constrained by the fragility of autoregressive source decoding. In low-SNR regimes, even a small number of residual bit errors after channel decoding may derail the subsequent lossless reconstruction process, especially when Arithmetic Coding (AC) relies on Large Language Model (LLM)-based probability estimation.