Helix 🧬: the first Humanoid Vision-Language-Action modelHelix understands speech, reasons through problems, and can grasp any object - all without needing training or code.
The video shows two humanoid robots performing collaborative grocery storage. A single set of Helix neural network weights runs simultaneously on two robots.
Helix is a novel architecture, "System 1, System 2"
System 2 is an internet-pretrained 7B parameter VLM (big brain)
System 1 is an 80M parameter visuomotor policy (fast control)
Each system runs on onboard embedded GPUs.
Here's the full technical writeup describing Helix's architecture, training, and inference details: https://www.figure.ai/news/helix#research #robotics #video