Perceptron open-sources Isaac 0.5, a 36B-parameter embodied foundation model spanning 35+ robots
AkshatS07 · x · 2026-09-10
Perceptron released Isaac 0.5, an open-source 36B-parameter sparse embodied foundation model claiming frontier multimodal video understanding, embodied reasoning and robot control. Trained on 35+ embodiments, 100K hours of robot data, 1M hours of video and 3T tokens, it introduces a data-mix scaling law: scaling general video from 1K to 1M hours cut required teleoperation data from 5,900 to 28 hours. Repetitive tasks like box packing fine-tune reliably with 30 episodes. Weights and paper are public.
Related event: Perceptron Open-Sources 36B Embodied Foundation Model Isaac 0.5(2 posts)→
More from Embodied
- RealSense D585 Pro AI-Powered 3D Stereo Depth Camera Unboxed for Physical AI — chrismatthieu · 2026-10-26
- Physical world agent swarm demo shared on X — pduan · 2026-10-26
- Looking for a wearable mic with best battery life that feeds recordings to personal agents via MCP — altryne · 2026-10-26
- 'Lamp Swarm': a desk of lamp-shaped robots shows what physical AI work looks like — dee_hw · 2026-10-26
- Tencent's HiSTEVE 1.0: hierarchical VLA agent plays Minecraft with native keyboard and mouse, hits 85% SOTA — _akhaliq · 2026-10-26
- SJTU's VaM lets robots learn online from mistakes, 95%+ success over 4-hour autonomous runs — chris_j_paxton · 2026-10-26