π MiniCPM enters the physical world β enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: π€ MiniCPM-RobotManip β a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. π MiniCPM-RobotTrack β a 0.5