Unverified50% confidenceFactExact time
Representative VLA works include RT-2 and OpenVLA, which are typically pretrained on massive image-text-action triplet data and possess a certain degree of open-world generalization capability.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRepresentative VLA works include RT-2, OpenVLA, π0, etc.79% similarVerifiedVLA models integrate visual perception, language understanding, and robot action planning into a unified model, typically using a pretrained large vision-language model as the backbone, with representative works including Google's RT-2 and OpenVLA.77% similarUnverifiedOpenVLA（2024年）是基于Llama 2架构的7B参数开源VLA模型，在Open X-Embodiment数据集上训练77% similarUnverifiedRTMPose is a real-time multi-person pose estimation framework developed by OpenMMLab, capable of outputting human keypoint coordinates at high frame rates.67% similarUnverifiedOpenVLA 由斯坦福等机构联合发布，是基于 Llama 架构的开源 VLA 基线67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046197API
curl https://kongchang.com/api/v1/knowledge/claims/1046197MCP
get_claim(id=1046197)