Metraipolis › archive › dc_64652cdbeb17

ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics — arXiv:2609.07838

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.07838
License (as archived): CC0-1.0
Archived: 2026-10-16T15:31:13.468Z
SHA-256 of the archived text: c0c762b9fa3726de6c5300505f700bf4841b007c6313cefaacf3817da13d8098
Stable URL of this page: https://metraipolis.com/documento/dc_64652cdbeb17

How to cite

ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics — arXiv:2609.07838 — arXiv (en), https://arxiv.org/abs/2609.07838 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64652cdbeb17 (Metraipolis archive dc_64652cdbeb17, sha256 c0c762b9fa3726de6c5300505f700bf4841b007c6313cefaacf3817da13d8098)

BibTeX

@misc{dc64652cdbeb17,
  title = {ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics — arXiv:2609.07838},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07838},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64652cdbeb17; sha256 c0c762b9fa3726de6c5300505f700bf4841b007c6313cefaacf3817da13d8098},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07838. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Connected robotics is an emerging 6G application where mobile robots follow natural-language instructions to manipulate physical objects. The Vision-Language-Action (VLA) models that enable this are too large to run on the robot; a common trend is to offload inference to the cloud. The wireless link, however, limits how much sensing data the edge can transmit per control step. Two recent lines address this constraint: semantic communication codecs compress sensor data but require channel-specific retraining, and VLA token pruners select tokens from image but ignore the channel. Our insight is that the dense semantic information contained in the language already indicates which visual tokens matter. We propose ComVLA, a framework that uses this language guidance to adapt the VLA token budget to the channel capacity. Transmitting 32 tokens instead of 512 on the LIBERO benchmark, ComVLA cuts inference compute by 74% and inference latency by 22% versus the original OpenVLA-OFT baseline, at a cost of 1.5 pp in average task success (95.4% vs. 96.9%), and it stays within the capacity budget under Rayleigh and Rician fading. These results demonstrate that co-designing VLA inference and wireless communication is a practical direction for 6G-connected robotics.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.07838 — 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 2026-10-16T15:11:47.606Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).