[KongchangAI]
Model

GR00T N1.7

A general-purpose humanoid robot foundation model released by NVIDIA, built on a VLA (vision-language-action) architecture and intended for general policy learning on humanoid robots.

Timeline (last 90 days)

Nov 19

A study of GR00T N1.7 found that when keywords in instructions are replaced with synonyms, the VLA policy may successfully select the target object yet fail to complete the task.

Unverified50%
Nov 19

GR00T N1.7 adopts a "VLM backbone + action expert" architecture, in which the connector is the interface module between the vision-language model and the action generator.

Unverified50%
Oct 13

VioLA can execute locomotion commands on a real robot without any task-specific fine-tuning, achieving a 100% success rate, compared with 16.7% for GR00T N1.7 and 0% for Ψ₀.

Unverified50%

All Facts (3)

Source Articles