Perceptron Releases Isaac 0.5: 36B Open Weight Embodied Foundation Model
lukas_m_ziegler · x · 2026-08-27
Perceptron has released Isaac 0.5, a 36B parameter dynamic MoE open-weight embodied foundation model. Isaac combines multimodal video understanding, embodied reasoning, and robot control into a single, sparse backbone.
Related event: Isaac 0.5 Released: Open-Weight 36B Dynamic MoE Embodied Foundation Model(4 posts)→
More from Embodied
- Figure's Index: 43k weekly users feeding robot data, $15M paid, $1B committed — coreylynch · 2026-08-27
- Perceptron trains Isaac on massive video data to reduce robot training needs — rohanpaul_ai · 2026-08-27
- NeurIPS 2026 Robot Learning Workshop extends submission deadline by 48 hours — m_wulfmeier · 2026-08-27
- Apple announces new Mac mini with M6 chip — power97992 · 2026-08-27
- Reverse engineering DJI: Understanding their low costs — yacineMTB · 2026-08-27
- Hacking WiFi driver for ultra-low latency drone control — yacineMTB · 2026-08-27