Introducing Isaac 0.5

An Open-Source Embodied Foundation Model Aug 26, 2026 Introducing Isaac 0.5 An Open-Source Embodied Foundation Model Aug 26, 2026 Introducing Isaac 0.5 An Open-Source Embodied Foundation Model Today we are releasing Isaac 0.5, our new open-source embodied foundation model.

To our knowledge, it is the first open model at the frontier of multimodal video understanding, embodied reasoning, and robot control.

Further, Isaac establishes a scaling law for trading off general video, egocentric, UMI, and teleop data.

The law provides a framework for choosing the appropriate mix of video and robot demonstrations as training scales, given a fixed budget and action loss target.

In our experiments, scaling general video from 1,000 to one million hours cut the teleoperation needed to reach well-calibrated held-out action loss from about 5,900 hours to 28.

Isaac is a 36-billion-parameter sparse model.

It reads images, video, language instructions, robot state, and previous actions.

It can answer questions about a video, point to objects and parts, track them over time, report task progress, and generate robot actions.

…