GR00T N1 is NVIDIA's humanoid foundation model combining vision-language understanding with action generation for cross-platform transfer.
RT-2 converts pretrained VLMs into robotic policies, enabling zero-shot generalization to novel instructions and objects.
Helix is an end-to-end neural framework for humanoid whole-body perception and manipulation, achieving high generalization through large-scale sim data and real-world fine-tuning.