Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Evidence-Backed Video Question Answering

First seen · 7/14/2026, 12:00 PMLatest activity · 7/14/2026, 12:00 PM

Salesforce AI Research introduces Evidence-Backed Video Question Answering (E-VQA), a task that requires Video LLMs to produce both semantic answers and precise spatio-temporal evidence: temporal segments plus dense tracked object segmentation masklets. The paper presents ST-Evidence, described as the first human-verified benchmark covering discriminative and generative pixel-level grounding, and ST-Evidence-Instruct, a 160k-scale automatically generated training set. Fine-tuning grounded Video LLMs reportedly improves a 7B model over a size-matched UniPixel baseline by 27.2 t-mean and 13.8 J&F.

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 Papers7/14, 12:00 PMnot independentRepresentative
    Evidence-Backed Video Question Answering