Unverified50% confidenceFactExact time
World Action Model通常采用视频生成模型作为骨干架构，代表性工作包括Google DeepMind的Genie系列和加州大学伯克利分校的UniSim
1
Sources
50%
Confidence
Long-term
Relevance
7/24/2026
First Seen
Sources
Related Claims
UnverifiedGoogle DeepMind提出了ReAct（Reasoning + Acting）代理循环模式69% similarUnverified学术界正探索基础模型在机器人领域的应用，如Google DeepMind的RT-2和斯坦福的Open X-Embodiment项目69% similarUnverifiedGoogle DeepMind推动了A2A（Agent-to-Agent）通信规范66% similarUnverifiedProject Genie是谷歌DeepMind推出的基础世界模型（Foundation World Model）项目65% similarUnverifiedGoogle此前在视频生成基础模型方面有Lumiere和VideoPoet等前期研究64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/602704API
curl https://kongchang.com/api/v1/knowledge/claims/602704MCP
get_claim(id=602704)