30B MoE Embodied Model Activates 3B Parameters
HeyToha · x · 2026-07-12
The post added that this model's training data differs from most video models: in addition to internet video, it incorporates over 70,000 hours of embodied data, including:
- Robotic manipulation
- Navigation
- First-person video
The author also noted the use of a 30B MoE architecture, where only 3B parameters are activated during generation, retaining larger capacity at a lower inference cost.
Related event: LingBot-VA/VLA 2.0 Released: Native Embodied Foundation Model(24 posts)→
More from Embodied
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- Polish developers build iPhone app that detects nearby Meta smart glasses — Low-Honeydew6483 · 2026-09-11
- Ant's Afu health AI hits 150M users, unveils AI+hardware health alliance at Bund Summit — APPSO · 2026-09-11
- Johns Hopkins Launches Full-Stack Hands-on Robot Learning Class with SO-101 Arm Kits — _krishna_murthy · 2026-09-11
- SyncWorld: In-Context Robot World Model Simulates Unseen Views and Embodiments Zero-Shot — ChongZzZhang · 2026-09-11
- A 3D Pose Dataset for Dogs Released — ducha_aiki · 2026-09-11