# Perceptron — Introducing Isaac 0.5

- Company: Perceptron (perceptron.inc)
- Announced: 2026-08-26
- Category: not stated
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.perceptron.inc/blog/introducing-isaac-0-5
- Record: https://forck.live/items/18608-introducing-isaac-0-5
- Subject: Perceptron Isaac / Perceptron Mk1

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. …

---

Record: https://forck.live/items/18608-introducing-isaac-0-5
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md