ResearcharXivNEW
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Wang 2026-10-14
Weijie WangHaomin ZhangYe Li
Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Passing prompts or recent frames between shots does not provide a shared spatial frame for revisiting a scene or a time-indexed record for replaying an earlier event. We present Any Time, Any Space (ATAS), which compiles a screenplay into shot request
Read on arXivData aggregated and editorially reviewed by TrendMing.
Key Contributions
- Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests.
- Passing prompts or recent frames between shots does not provide a shared spatial frame for revisiting a scene or a time-indexed record for replaying an earlier event.
- We present Any Time, Any Space (ATAS), which compiles a screenplay into shot request
Research Themes
AIResearch