Metraipolis › archive › dc_7b224c40deae

SCORAS-MoE: Joint Compression and Resource-Adaptive Deployment of MoE-VLMs in LEO Satellite Networks — arXiv:2609.36763

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36763
License (as archived)
CC0-1.0
Archived
2026-10-07T17:59:37.841Z
SHA-256 of the archived text
9316e2ff0ded3cf174eb74606afab91d0cb2775c62ff517ae334a730cc8b6aab
Stable URL of this page
https://metraipolis.com/documento/dc_7b224c40deae

How to cite

SCORAS-MoE: Joint Compression and Resource-Adaptive Deployment of MoE-VLMs in LEO Satellite Networks — arXiv:2609.36763 — arXiv (en), https://arxiv.org/abs/2609.36763 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b224c40deae (Metraipolis archive dc_7b224c40deae, sha256 9316e2ff0ded3cf174eb74606afab91d0cb2775c62ff517ae334a730cc8b6aab)
BibTeX
@misc{dc7b224c40deae,
  title = {SCORAS-MoE: Joint Compression and Resource-Adaptive Deployment of MoE-VLMs in LEO Satellite Networks — arXiv:2609.36763},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36763},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b224c40deae; sha256 9316e2ff0ded3cf174eb74606afab91d0cb2775c62ff517ae334a730cc8b6aab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36763. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying large vision-language models (VLMs) onboard satellites enables onboard data processing and reduces raw data downlink. However, onboard inference faces two resource challenges. Limited onboard memory and energy require model compression and distributed deployment. Dynamic resource availability requires fast deployment decisions as illumination, battery levels, and communication conditions change. We present SCORAS-MoE, a joint compression and deployment framework for mixture-of-experts (MoE) VLMs in low Earth orbit (LEO) satellite networks. To address limited resources, SCORAS-MoE measures the perturbation of the routed MoE output caused by low-rank approximation, assigns higher ranks to more sensitive experts, and distributes compressed model shards across satellites for cooperative inference. The compressed models yield profiles of measured accuracy and inference energy. To adapt to dynamic resources, the online scheduler selects profile compositions and shard placements in each slot. For each candidate composition, it reduces placement to a minimum-cost assignment problem solved by the Hungarian algorithm, while enumerating the compositions yields the optimal deployment for the current-slot objective. Experiments on Qwen3-VL-30B-A3B-Instruct show that allocating ranks based on output perturbation is particularly effective under aggressive compression, with an absolute gain of $3.7\%$ in mean accuracy over uniform rank allocation when expert projections retain $30\%$ of their original parameters. The fixed-profile scheduler achieves higher throughput with fewer service switches and lower battery impact than the evaluated proximal policy optimization (PPO) and evolutionary baselines, with respective speedups of $8.7\times$ and $183.5\times$. Adaptive profile selection further improves the balance between service quality and energy use.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-30 in cs.NI).
Categorie arXiv: Networking and Internet Architecture (cs.NI).
Pagina del lavoro: https://arxiv.org/abs/2609.36763 — 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 2026-10-07T17:33:10.174Z dalla pagina https://arxiv.org/catchup/cs.NI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).