← Search

Sang-Hyo Kim

3 accepted papers

2026

Efficient Message-Passing Transformer for Error Correcting Codes

ICLR 2026poster

Error correcting codes (ECCs) are a fundamental technique for ensuring reliable communication over noisy channels. Recent advances in deep learning have enabled transformer-based decoders to achieve state-of-the-art performance on short codes; however, their computational complexity remains signific…

Cited by 0SourcecodeScholar
2025

CrossMPT: Cross-attention Message-passing Transformer for Error Correcting Codes

ICLR 2025poster

Error correcting codes (ECCs) are indispensable for reliable transmission in communication systems. Recent advancements in deep learning have catalyzed the exploration of ECC decoders based on neural networks. Among these, transformer-based neural decoders have achieved state-of-the-art decoding per…

Cited by 6SourcePDFScholar
2023

Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

NeurIPS 2023poster

Low-density parity-check (LDPC) codes have been successfully commercialized in communication systems due to their strong error correction capabilities and simple decoding process. However, the error-floor phenomenon of LDPC codes, in which the error rate stops decreasing rapidly at a certain level,…