Multimodal Action Models

We’re building large scale "generalist" models capable of doing dozens of tasks across numerous modalities, starting with language, images, RL and control tasks. Check out the links below to learn more!

Icon

Roadmap

Learn more about the Multimodal Action Models project roadmap

Icon

Github Repository

Explore Multimodal Action Models project on Github

Icon

Discord Channel

Join the Multimodal Action Models project Discord Channel

Great! You’ve successfully signed up.
Welcome back! You've successfully signed in.
You've successfully subscribed to Manifold Research Group.
Your link has expired.
Success! Check your email for magic link to sign-in.
Success! Your billing info has been updated.
Your billing was not updated.