Google Research·· 7 d ago
Automating coherent long-form video generation
Automating coherent long-form video generation
AI summary
Google Research published research on long-form video generation, proposing an AI video co-director multi-agent orchestration framework built on Gemini and Veo to plan visual continuity across multi-shot narratives.
Selection record
Threshold 60Official, first-handFirst 62Second 71
AdmittedSum of both 133 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：多智能体AI视频生成框架与评测
- Why it was chosen
- Dividing long-form video generation into four agents and reporting evaluations of multi-shot consistency and character retention outlines one engineering route for longer video generation.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google Research · research.google