RewardAI unveils OM-1, a robot foundation model that zero-shot generalizes across arms and humanoids
yifengzhu_ut · x · 2026-09-15
RewardAI has introduced OM-1, its first robot foundation model, which zero-shot generalizes to table-top arms, industrial arms, and humanoids. The team says it was learned directly from human manipulation data with no teleop or robot data, achieving near human-level dexterity and efficiency plus multi-robot collaboration. Observers highlighted how smooth the resulting motions look.
Related event: Physical Intelligence unveils OM-1 robot foundation model(31 posts)→
More from Embodied
- Wayve researcher: robotics unlikely to find objectives far beyond next-token prediction — m_wulfmeier · 2026-09-15
- UBTECH keeps reusing its human-robot slow dance clip, even at factory opening — TinfoilTricorn · 2026-09-15
- The Biggest Market for Humanoid Robots Today Is Marketing, By a Wide Margin — NYCounihan · 2026-09-15
- Fruit fly brain mapped over 20 years plays Minecraft on its own within 7 days — udmrzn · 2026-09-15
- Fruit fly brain with 166,700 neurons installed in a physical robot that walks — udmrzn · 2026-09-15
- Skild AI Hits $100M ARR 10 Months After First Deployment, 60+ Customers — lukas_m_ziegler · 2026-09-15