Unverified50% confidenceFactExact time
Google's RT series models, the Toyota Research Institute's Diffusion Policy, and Vision-Language-Action (VLA) models are early attempts toward world task models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/4/2026
First Seen
Valid until: 12/3/2026
Sources
Related Entities
Related Claims
UnverifiedGoogle于2023年发布RT-2等视觉-语言-动作模型（VLA），将感知、语义理解与操作策略统一在同一Transformer框架中75% similarUnverifiedVLA的代表性工作包括Google的RT-2（Robotics Transformer 2）和Physical Intelligence公司的π0模型66% similarUnverifiedWorld 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UniSim66% similarUnverifiedGoogle's RT-2 demonstrated that vision-language models can directly output robot action instructions.65% similarUnverifiedGoogle DeepMind的RT-2（2023年）将机器人动作词元化为离散token，附加到视觉-语言模型PaLI-X和PaLM-E的输出词汇表中，展现出零样本泛化能力64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/854131API
curl https://kongchang.com/api/v1/knowledge/claims/854131MCP
get_claim(id=854131)