Scaling Vision-Language-Action Models with 100K+ Hours of Real-World Data
AI & ML interests
None defined yet.
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 • 1.34k • 16 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABC_D
Robotics • 5B • Updated • 55 • 1 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABCD_D
Robotics • 5B • Updated • 51 • 3 -
XiaomiRobotics/Xiaomi-Robotics-0-SimplerEnv-WidowX
Robotics • 5B • Updated • 97 • 3
Unified embodied synthesis model that bridges foundation image generation and embodied world modeling
-
XiaomiRobotics/Xiaomi-Robotics-U0-FlashAR
Any-to-Any • 38B • Updated • 47 • 11 -
XiaomiRobotics/Xiaomi-Robotics-U0
Any-to-Any • 34B • Updated • 67 • 32 -
XiaomiRobotics/Xiaomi-Robotics-U0-4B
Image-Text-to-Image • 5B • Updated • 57 • 13 -
XiaomiRobotics/Xiaomi-Robotics-U0-Sequence
Any-to-Any • 34B • Updated • 55 • 5
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-U0-FlashAR
Any-to-Any • 38B • Updated • 47 • 11 -
XiaomiRobotics/Xiaomi-Robotics-U0
Any-to-Any • 34B • Updated • 67 • 32 -
XiaomiRobotics/Xiaomi-Robotics-U0-4B
Image-Text-to-Image • 5B • Updated • 57 • 13 -
XiaomiRobotics/Xiaomi-Robotics-U0-Sequence
Any-to-Any • 34B • Updated • 55 • 5
-
XiaomiRobotics/Xiaomi-Robotics-0-LIBERO
Robotics • 5B • Updated • 1.34k • 16 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABC_D
Robotics • 5B • Updated • 55 • 1 -
XiaomiRobotics/Xiaomi-Robotics-0-Calvin-ABCD_D
Robotics • 5B • Updated • 51 • 3 -
XiaomiRobotics/Xiaomi-Robotics-0-SimplerEnv-WidowX
Robotics • 5B • Updated • 97 • 3