Steertuning Policies from a Few Human Videos
Overview
Source roundup from published reports. Claims below are attributed to their publishers, not independently verified. arXiv Robotics — research abstracts: Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration. Dex-One2Many is a real-to-sim-to-real framework that learns a generalizable dexterous manipulation policy from a single human video. By abstracting the video into sequential scene graphs, the method guides reinforcement …
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“oration short and guided. Trained entirely in simulation, Dex-One2Many transfers zero-shot to a real multi-fingered hand. Across five tool-use and manipulation tasks, Dex-One2Many exceeds baselines by 6.5% in seen configurations, while its robust generalization widens this gap to 71% in unseen scenarios.”
Exact source · revision 1Source owner not reported
Evidence dependency changes (1)
- 2026-10-15T20:57:37.358Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsLearning to See through Action: Predictive Curiosity for Robots
Robots improve visual learning by combining predictive curiosity with reconstruction. Experiments show predictive curiosity enhances visual learning beyond visual novelty alone.
- arXiv Robotics — research abstractsDex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
Dex-One2Many is a real-to-sim-to-real framework that learns a generalizable dexterous manipulation policy from a single human video. By abstracting the video into sequential scene graphs, the method guides reinforcement learning to enable efficient exploration and broad generalization. It outperforms baselines by 6.5% in seen configurations and achieves a 71% performance gap in unseen scenarios when transferred to a real multi-fingered hand.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).