Unlike LLMs, we can’t scrape the internet for robot data
Announcing Project Go-Big: we’re building the world's largest humanoid pretraining dataset
This is accelerated by our partnership with Brookfield, who owns over 100,000 residential units
Announcing Project Go-Big: we’re building the world's largest humanoid pretraining dataset
This is accelerated by our partnership with Brookfield, who owns over 100,000 residential units
Helix is now learning directly from human video data
We have already trained on data collected in the real world, including Brookfield residential units
To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video
We have already trained on data collected in the real world, including Brookfield residential units
To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video
Every machine learning breakthrough has come from massive, diverse datasets. There is nothing like this for robotics so we are building our own
A single Helix neural network now outputs both manipulation and navigation, end-to-end from language and pixel input
A single Helix neural network now outputs both manipulation and navigation, end-to-end from language and pixel input
We posted a write-up on the website about our plans to build an internet-scale pretraining data set and the results we have seen so far
figure.ai/news/project-g…
figure.ai/news/project-g…
If you are interested in helping us scale Helix and build the world’s largest pretraining dataset, apply here:
figure.ai/careers
figure.ai/careers
• • •
Missing some Tweet in this thread? You can try to
force a refresh
