Back to Articles
TL;DR What is GR00T N1.7? Training on Human EgoCentric Video Data Inference & Deployment Fine-Tuning on Your Robot We are releasing NVIDIA Isaac GR00T N1.7 (Early Access) — an open, commercially licensed Vision-Language-Action model for humanoid robots, built on a simple premise: human data is the most scalable source of robot intelligence.
TL;DR
What is GR00T N1.7?
GR00T N1.7 is a 3B-parameter open reasoning Vision-Language-Action (VLA) model that maps visual observations and natural language instructions to continuous robot actions. It uses an Action Cascade architecture — a dual-system design that separates high-level reasoning from low-level motor control:
