Dyna Robotics says its world action model can generate both actions and videos, enabling it to generate training data for itself.

“3D environments,”

“we have also used our own world model,”

“right,”

“the world action model I was telling you about because the model not only generates action, can also generate videos the model can also generate its own training data so that becomes a, you know, self-fulfilling like flywheel that I think will also be powerful”