Perceptron releases open Isaac 0.5 embodied foundation model
Perceptron released Isaac 0.5, a 36-billion-parameter sparse model spanning multimodal video understanding, embodied reasoning and robot control, together with weights, code and a technical report.
Evidence notes
- Isaac 0.5 accepts images, video, language instructions, robot state and previous actions, and can return grounded visual outputs, task progress or robot actions.
- Training combined more than 35 robot systems, 100,000 hours of robot experience, one million hours of general video and three trillion multimodal tokens.
- Perceptron published model weights on Hugging Face, training and inference code on GitHub, and a technical report; LeRobot support is included.
Company context
Perceptron develops vision and embodied-AI models for robots and other physical systems. Its model stack combines video understanding, spatial grounding, task-progress reasoning and robot control, with open Isaac releases and a commercial perceptive-language API.