Metraipolis › archive › dc_021350d2a256

Demo: Real-time Generative Multicasting with On-Device Intent-aware Semantic Decomposition — arXiv:2608.14600

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14600
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:53.963Z
SHA-256 of the archived text
b84872ec43e45d197a1c08f8bebbab679afcb5088bece3163f6c09c862167678
Stable URL of this page
https://metraipolis.com/documento/dc_021350d2a256

How to cite

Demo: Real-time Generative Multicasting with On-Device Intent-aware Semantic Decomposition — arXiv:2608.14600 — arXiv (en), https://arxiv.org/abs/2608.14600 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_021350d2a256 (Metraipolis archive dc_021350d2a256, sha256 b84872ec43e45d197a1c08f8bebbab679afcb5088bece3163f6c09c862167678)
BibTeX
@misc{dc021350d2a256,
  title = {Demo: Real-time Generative Multicasting with On-Device Intent-aware Semantic Decomposition — arXiv:2608.14600},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14600},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_021350d2a256; sha256 b84872ec43e45d197a1c08f8bebbab679afcb5088bece3163f6c09c862167678},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14600. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a demonstration for generative multicasting with on-device, intent-aware semantic decomposition. At the transmitter, DNN-based segmentation extracts a semantic map from the source video, decomposing it into multiple sub-signal classes based on multi-user receiver intents. The transmitter broadcasts the semantic map to all users over shared wireless/network resources, thereby utilizing orthogonal resources only to transmit the sub-signal classes intended for each user. Users partially reconstruct and partially synthesize the signal by combining the received intended classes with non-intended classes locally synthesized by a generative model from the semantic map. We derive the rate-distortion/perception curves for reconstruction/synthesis with the generative model, to adaptively set compression rates for the semantic map and intended classes. Generative multicasting significantly reduces the wireless/network resources required for existing/emerging multimedia multicasting applications. The system is real-time on a Google Coral Edge TPU with 4 TOPS (int8). This is the first demonstration of generative multicasting representing a substantial advancement in on-device generative SemCom.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Networking and Internet Architecture (cs.NI) ; Machine Learning (cs.LG); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.14600 — 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 2026-10-18T19:02:44.208Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).