Robot learning has advanced by scaling demonstration datasets and model capacity; however, deploying a new robot embodiment or task typically necessitates a dedicated teleoperation corpus. The resulting policies remain bounded by their imitation distributions, limiting generalization and continual self-improvement. We...
Run-Han Huang, Xiang-Cheng Zhang, Hao-Yu Chen et al.· 3 citations
This work takes an RSI-inspired approach at the harness layer, scaling auto-research loops across increasingly numerous and diverse environments for harness rollouts, and yields reusable improvements that transfer beyond their development setting.
Hao-Zhe Liu, Tian Ye, Sen-Sen Gao et al.· arXiv.org· 13 citations
The results show that systematic GRPO post-training can substantially improve flow-based VLA policies without additional private demonstrations, and outperforms the published sota models.
Lang Cao, Renhong Chen, Luyi Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.