Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?

First seen · 8/6/2026, 04:00 AMLatest activity · 8/6/2026, 04:00 AM

GST-Bench evaluates whether vision-language models can integrate long video streams into a globally consistent spatial representation. Its human-verified VQA questions are derived from 6,790 minutes of synthetic video and require reasoning from unseen viewpoints and mapping egocentric observations onto top-down images. Across 22 state-of-the-art VLMs, the strongest zero-shot result reported is 42.68, compared with a human score of 79.08. The authors also introduce GST-Bench-Local to distinguish local perception from global integration failures, plus GST-Train as a training resource for global spatial reasoning.

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. AggregatorHuggingFace Daily Papers8/6, 04:00 AMnot independentRepresentative
    GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?