SemantIC-Mamba: Enhancing Semantic Fidelity with Mamba-Based Global Context Modeling for 6G Communications
Electronics · 30.03.2026 · 15 (7) · 1444
DOI: 10.3390/electronics15071444 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 30.03.2026. Verfasst von Bora Yoon und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and ICT https://ror.org/01wpjm123.
Abstract (Originalsprache)
This paper proposes semantic interference cancellation (SemantIC)-Mamba, a novel framework that enhances semantic reconstruction accuracy while stably maintaining channel decoding performance. The proposed model follows a turbo structure in which information is complementarily exchanged between the semantic domain and the signal domain, progressively refining the reconstruction quality through iterative processing. To effectively perform this iterative information refinement, the proposed framework adopts a semantic autoencoder composed of three key components: a Conv block that extracts local features, a Mamba block that efficiently models long-range dependencies to integrate global contextual information, and an UpConv block that restores low-resolution features to the original resolution. Experimental results demonstrate that SemantIC-Mamba consistently achieves improved PSNR and classification accuracy compared to conventional SemantIC and SemantIC++ while maintaining channel decoding performance at a level comparable to existing models.
Förderung
- Ministry of Science and ICT https://ror.org/01wpjm123
Zitieren
APA
Yoon, B., Kim, J., & Song, H. (2026). SemantIC-Mamba: Enhancing Semantic Fidelity with Mamba-Based Global Context Modeling for 6G Communications. Electronics, 15(7), 1444. https://doi.org/10.3390/electronics15071444
Vancouver
Yoon B, Kim J, Song H. SemantIC-Mamba: Enhancing Semantic Fidelity with Mamba-Based Global Context Modeling for 6G Communications. Electronics. 2026;15(7):1444. doi:10.3390/electronics15071444
BibTeX
@article{Yoon2026,
author = {Yoon, Bora and Kim, Junghyun and Song, Hong-Yeop},
title = {SemantIC-Mamba: Enhancing Semantic Fidelity with Mamba-Based Global Context Modeling for 6G Communications},
journal = {Electronics},
year = {2026},
volume = {15},
number = {7},
pages = {1444},
doi = {10.3390/electronics15071444}
}
EUVIMED