Peking University's Open-HumanWAM: open recipe scales human experience to 88.65% on RoboTwin
CyberRobooo · x · 2026-11-19
Peking University's DA Group released Open-HumanWAM, a fully open recipe (paper, code, models, datasets) for embodied foundation models that learn from human experience: egocentric video + language + hand-motion pretraining, then robot post-training, scaling from 100 to 50,000 hours of human data. Results: RoboTwin zero-shot 13.94% (rank 1 open-source, no task-specific post-training), 88.65% post-trained (rank 1 in reported comparisons), and real-robot zero-shot improving from 20.0% to 30.5% with human-robot hybrid data. Deployed on Astribot S1, it demos multi-stage household tasks including a 14-stage desk organization sequence.
Related event: Peking University open-sources Open-HumanWAM for household robots(2 posts)→
More from Embodied
- STASIS (YC F26) launches smart glasses with 6 sensors tracking eye strain at 92% accuracy — LinusEkenstam · 2026-11-20
- NVIDIA's GR00T 2 Controls Real Dexterous Hands End to End, Fully Onboard — rsasaki0109 · 2026-11-20
- NUS MAGIC Lab recruits 2 PhD students and research engineers for physical AI robotics — DJiafei · 2026-11-20
- Unitree demos its R1 humanoid robot for students at UT Dallas — YuXiang_IRVL · 2026-11-20
- First Cybercab robotaxi rides reported in Dallas — EricETesla · 2026-11-20
- ETH Zurich launches Embodied AI Lab (ZEAL), hiring first PhD students — breadli428 · 2026-11-20