Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

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

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement

First seen · 7/6/2026, 10:25 AMLatest activity · 7/6/2026, 10:25 AM

G2VD targets shortcut learning in AI-generated video detectors, which often perform poorly on videos from unseen generators. Its counterfactual intervention pipeline uses VAE reconstruction followed by frequency- and pixel-domain alignment to weaken correlations between generator-specific biases and authenticity labels. A two-branch causal disentanglement classifier, regularized with the Hilbert-Schmidt Independence Criterion, separates intrinsic forensic cues from domain-specific information. The authors report consistent cross-domain gains across four public datasets and more than 90% overall accuracy on GenVidBench using only 10% of the available training data.

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. AggregatorarXiv7/6, 10:25 AMnot independentRepresentative
    G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement