H3-World: Turning Language Understanding into World Control
[Widzenie komputerowe] Autorzy: Danze Chen, Zeqing Wang, Ziyue Lin i 2 więcej
We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as large video generators become more capable, language is emerging as a natural interface for control. MiniMax-H3, for example, already supports zero-shot control of character behavior and camera motion through natural-language instructions. Building on this, H3-World turns this coarse language interface into precise, temporally grounded world control, without introducing dedicated action modules. Specifically, we represent each action as a structured combination of character and camera instructions, and align them with the corresponding temporal video latents. To make the control temporally precise, we further introduce temporal attention routing, which restricts each instruction to its intended time interval and reduces control leakage ac…
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe