Metraipolis › archive › dc_ef97dfa58e4f

Closing the Semantic-Edge Gap: Tiny Language Models for 6G Wireless Intelligence — arXiv:2609.03747

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03747
License (as archived)
CC0-1.0
Archived
2026-10-17T03:23:03.956Z
SHA-256 of the archived text
e64fde0547c5f30c3791a1bb15a212ed3ac918f335ea7e4d338a5d1080c74834
Stable URL of this page
https://metraipolis.com/documento/dc_ef97dfa58e4f

How to cite

Closing the Semantic-Edge Gap: Tiny Language Models for 6G Wireless Intelligence — arXiv:2609.03747 — arXiv (en), https://arxiv.org/abs/2609.03747 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef97dfa58e4f (Metraipolis archive dc_ef97dfa58e4f, sha256 e64fde0547c5f30c3791a1bb15a212ed3ac918f335ea7e4d338a5d1080c74834)
BibTeX
@misc{dcef97dfa58e4f,
  title = {Closing the Semantic-Edge Gap: Tiny Language Models for 6G Wireless Intelligence — arXiv:2609.03747},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03747},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef97dfa58e4f; sha256 e64fde0547c5f30c3791a1bb15a212ed3ac918f335ea7e4d338a5d1080c74834},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03747. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sixth-generation (6G) wireless networks are envisioned as AI-native systems in which semantic communication - transmitting task-relevant meaning rather than raw bits - moves beyond Shannon's classical bit-pipe model. Large language models (LLMs) dominate semantic encoding but are unsuitable for 6G user equipment and IoT devices, given prohibitive memory, energy, and latency costs. Tiny language models (TinyLMs) - compressed via TinyML techniques into kilobyte-to-megabyte memory and milliwatt power budgets - are the missing bridge between LLM-level semantic encoding and 6G edge hardware, yet no prior work systematically maps TinyML techniques onto semantic communication architectures for this purpose. This survey closes that gap through a two-axis taxonomy connecting six compression families (quantization, pruning, knowledge distillation, low-rank adaptation, neural architecture search, hybrid pipelines) to five semantic communication architectures (end-to-end joint source-channel coding, split learning, federated learning, knowledge-graph-assisted, and multi-task/cross-modal communication), synthesized with a quantitative meta-analysis of the model-size-versus-semantic-fidelity Pareto frontier. Representative results include a CNN-Transformer encoder achieving 22 dB PSNR at 33.33% semantic-representation size reduction; a symbolic protocol machine reducing a neural MAC protocol from 4.55 MB to 1 KB (99.98% smaller) with zero performance loss; federated bidirectional knowledge distillation converging under joint model-and-data heterogeneity where FedAvg-style averaging underperforms; and knowledge-graph-assisted probability graphs cutting transmission energy by 65%. The survey identifies nine open research challenges for TinyLM-enabled 6G semantic communication, including two not previously articulated in the literature.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in eess.SP).
Categorie arXiv: Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2609.03747 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T03:09:04.258Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).