Riemann-1.0 Tops Household Robot Leaderboards
量子位 · wechat · 2026-07-19
Riemann Dynamics released Riemann-1.0, a world action model for general-purpose robot manipulation, achieving a new high of 62.6% on RoboCasa-365 to claim SOTA. The article emphasizes that the key isn't simply piling up robot trajectories; instead, it incorporates a massive amount of human egocentric (first-person) video—making up the bulk of its **23.2 million hours of training data**—combined with a small amount of real robot and simulation data. This translates "watching how humans work" into executable robotic actions. The author breaks down the entire engineering pipeline: using an automated pipeline to clean and segment human videos, reconstructing 3D hand trajectories, and finally combining diffusion-based action-video joint modeling with staged training to merge world understanding with embodiment action adaptation. Ablation studies show that introducing human videos boosted the RoboCasa-365 success rate from 48.2% directly to 62.6%; in EgoVLA scenarios, the success rate of long-horizon, multi-stage tasks also jumped from 42.96% to 71.11%.
More from Embodied
- Generative Bionics turns its Gene.01 humanoid from CES concept into a walking platform — CyberRobooo · 2026-07-21
- Auki pitches physical AI infrastructure for stores, warehouses and supply chains — broodsugar · 2026-07-21
- Safe RL paper on directional constraints accepted to IROS 2026 — Jan_R_Peters · 2026-07-21
- Sunday Robotics says one example can teach its home robot a new behavior — saranormous · 2026-07-21
- San Francisco event seeks sponsors for the first 6-foot humanoid robot fight — cixliv · 2026-07-21
- Tiny memristor chip brings brain-model inference under 10 ms — striketheviol · 2026-07-21