Embodied AI TopConf · ICLR2026

Vid2World: Crafting Video Diffusion Models to Interactive World Models

ICLR2026 / World Models

世界模型策略学习视频
新标签打开 AlphaXiv
Vid2World: Crafting Video Diffusion Models to Interactive World Models figure
AlphaXiv 中文论文页面（可滚动查看）