Scaling Vision-Language-Action Models with 100K+ Hours of Real-World Data
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
-
XiaomiRobotics/Xiaomi-Robotics-0-LIBERO
Robotics • 5B • Updated • 3.61k • 15 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABC_D
Robotics • 5B • Updated • 50 • 1 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABCD_D
Robotics • 5B • Updated • 47 • 3 -
XiaomiRobotics/Xiaomi-Robotics-0-SimplerEnv-WidowX
Robotics • 5B • Updated • 85 • 2
Scaling Vision-Language-Action Models with 100K+ Hours of Real-World Data
Unified embodied synthesis model that bridges foundation image generation and embodied world modeling
-
XiaomiRobotics/Xiaomi-Robotics-0-LIBERO
Robotics • 5B • Updated • 3.61k • 15 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABC_D
Robotics • 5B • Updated • 50 • 1 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABCD_D
Robotics • 5B • Updated • 47 • 3 -
XiaomiRobotics/Xiaomi-Robotics-0-SimplerEnv-WidowX
Robotics • 5B • Updated • 85 • 2