Humanoid whole-body training data from robot-specific video generationExpert
KinoGen: Customizable Humanoid Loco-Manipulation References via Kinematically Grounded Video Generation
A Cornell and Multiply Labs preprint generates training motions for a humanoid by having a video model imagine the robot itself doing the task, then fitting the exact robot and object models to that video. Policies trained on these references succeeded 57% of the time in simulation against 42% for the best human-video pipeline, and four tasks ran on a real Unitree G1 with dexterous hands.