G0.5 from Galaxea is now available in LeRobot
LeRobot has released the G0.5 vision-language-action model from Galaxea. This 2B parameter model, built on Qwen3.5, predicts subtasks, object bounding boxes, and actions before each action chunk. The integration also enables the annotation pipeline to generate plans, memory, and visual Q&A for datasets, facilitating longer, more complex multi-step setups.
LeRobot has integrated the G0.5 vision-language-action model, a 2B parameter system built on Qwen3.5 from Galaxea, which predicts subtasks, object bounding boxes, and actions before each action chunk; the platform's annotation pipeline is also noted for generating plans, memory, and visual Q&A to support complex multi-step setups.
Source: LeRobot — X · Read original article ↗
Article text · Original source · English
G0.5 from Galaxea is now available in LeRobot! 🤖
G0.5 is a 2B vision-language-action model built on Qwen3.5.
Before each action chunkmit predicts:
- the current subtask ("pick up the red cube") from the overall task
- bounding boxes around the objects involved
- then the actions, which are conditioned on that reasoning
LeRobot's annotation pipeline can also generate plans, memory and visual Q&A into your datasets, opening the door to longer, more complex multi-step setups for future policies!
Thanks to the Galaxea team for the open release!
Links to the blog, docs and our walkthrough in the comments 👇
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: not_reported
- weights: not_reported
- dataset: not_reported
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
G0.5 from Galaxea is now available in LeRobot! 🤖
Open source S1
Source：LeRobot · x.com