Execution Logs Can Mislead Visual Judges in Video-Generation Agents

Holding video frames fixed, the study shows that auxiliary text can sharply distort some multimodal models’ assessments of whether requested events occurred.

Research Lab
Jian Xu

RIKEN

Research Digest··3 min read
Xu tests whether video-generation verifiers judge visual evidence independently from plans, narration and execution logs.

The author assembled 109 generated two-event clips with manual labels, including near misses where one requested event was visible but the other was absent.

Why this paper

From RIKEN

In one line

Execution traces cause video-generation verifiers to judge clips based on text, not visuals.

What we could check

  • ·No code link found
  • ·No weights link found
  • ·No dataset link found
  • ·No compute details found
  • ·No stated limitations found
  • ✓Reports numbers on named benchmarks (3 benchmarks)

Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.

§
newspaper

Research Digest

Articles published under the Zotpaper byline are synthesized from multiple source publications by our AI editor and reviewed by our editorial process. Each story combines reporting from credible outlets to give readers a balanced, comprehensive view.