Unverified50% confidenceFactExact time
Representative works in VLA models include Google's RT-2, OpenVLA, and π0.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedVLA的代表性工作包括Google的RT-2（Robotics Transformer 2）和Physical Intelligence公司的π0模型78% similarUnverifiedGoogle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71% similarUnverifiedGoogle's RT series models, the Toyota Research Institute's Diffusion Policy, and Vision-Language-Action (VLA) models are early attempts toward world task models.71% similarUnverifiedGoogle possesses full-stack AI capabilities spanning from TPU chips to Gemini models to end-user applications, distinguishing it from OpenAI's model of relying on Microsoft Azure and NVIDIA GPUs.59% similarUnverifiedGLM 4.7和Minimax M2.1均采用开源策略，模型权重公开可用59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995543API
curl https://kongchang.com/api/v1/knowledge/claims/995543MCP
get_claim(id=995543)