Metraipolis › archive › dc_762e44e498bd

From Single-Shot QA to Continuous Perception: Revisiting the Energy Composition and Optimization Boundary of Edge VLMs — arXiv:2611.00036

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00036
License (as archived)
CC0-1.0
Archived
2026-11-03T18:15:48.374Z
SHA-256 of the archived text
0600a4cc510ae3554e71d574144b700136b8db1edd22c1fa6c23e34851168ff1
Stable URL of this page
https://metraipolis.com/documento/dc_762e44e498bd

How to cite

From Single-Shot QA to Continuous Perception: Revisiting the Energy Composition and Optimization Boundary of Edge VLMs — arXiv:2611.00036 — arXiv (en), https://arxiv.org/abs/2611.00036 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_762e44e498bd (Metraipolis archive dc_762e44e498bd, sha256 0600a4cc510ae3554e71d574144b700136b8db1edd22c1fa6c23e34851168ff1)
BibTeX
@misc{dc762e44e498bd,
  title = {From Single-Shot QA to Continuous Perception: Revisiting the Energy Composition and Optimization Boundary of Edge VLMs — arXiv:2611.00036},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00036},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_762e44e498bd; sha256 0600a4cc510ae3554e71d574144b700136b8db1edd22c1fa6c23e34851168ff1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00036. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual-prefill energy conclusions for edge vision-language models (VLMs) are commonly drawn under single-shot workloads; we revisit them under continuous perception. Profiling nine VLMs across three architecture families on Jetson AGX Thor and Orin (4,508 records, calibrated with a pure-text task), we find two mutually independent energy laws: the per-output-token decode cost grows monotonically with model scale, whereas the visual-prefill (image-encoding) cost is dominated by visual-encoder architectural efficiency, not scale. Under continuous perception ($N{=}10$) with sparse output, visual-prefill energy reaches 92--97\% of total. We derive optimization strategies---visual frame reuse, adaptive output truncation, task-aware routing, and encoder throughput optimization---for edge VLM deployment.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00036 — 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 2026-11-03T18:09:53.473Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).