Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Seeing Is Free, Speaking Is Not: Output Decoding Dominates Edge VLM Energy

First seen · 7/10/2026, 11:31 PMLatest activity · 7/10/2026, 11:31 PM

This paper profiles five vision-language models across three architecture families, four image resolutions, and two platforms: an NVIDIA RTX 3070 and Jetson Orin NX. It reports that average inference power varies by less than 5% across resolutions, image complexity, and prompt types. Each output token takes 11–39 times more wall-clock time than an input token, making decoding the dominant energy cost. Image complexity can create up to 4.1× energy differences at the same resolution because it changes output length. Visual-token pruning saves at most 10% for fixed-token models, while output-length control saves up to 97%.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/10, 11:31 PMnot independentRepresentative
    Seeing Is Free, Speaking Is Not: Output Decoding Dominates Edge VLM Energy