Expired50% confidenceFactExact time
DeepMind employs two collaborating modules: the ER model (essentially a VLM), which is better at reasoning, handles coordination and planning, while the VLA model is responsible for executing physical actions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/18/2026
First Seen
Valid until: 10/16/2026(expired)
Sources
Related Claims
UnverifiedDeepMind developed the VLA (Vision-Language-Action model) system, which treats the robot's physical actions on equal footing with visual tokens and language tokens.81% similarUnverifiedVision-Language-Action (VLA) models are the latest paradigm for embodied intelligence, with representative works including Google DeepMind's RT-2 and Physical Intelligence's π0.77% similarUnverifiedDeepMind layered a Gemini model on top of its VLA, allowing users to issue instructions directly in natural language so the robot can carry on a conversation while working.71% similarUnverifiedRepresentative VLA model works include Google DeepMind's RT-2 and Stanford's OpenVLA.69% similarUnverifiedDeepMind的DreamerV1/V2/V3系列将潜空间梦境训练范式系统化，并在多个基准上验证了其有效性67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/552112API
curl https://kongchang.com/api/v1/knowledge/claims/552112MCP
get_claim(id=552112)