Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yanming Shao

Yanming Shao

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Robotics×2AI×2

Frequent co-authors

Zhongxi Chen2×
Yifan Han2×
Huanming Liu2×
Congsheng Xu2×
Xiaoyu Chen2×
Yao Mu2×

Research Timeline

2026
BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models

BORA is an offline-to-online RL framework that enhances dexterous VLA models for real-world robotics by using an action-conditioned critic and a lightweight residual adaptation mechanism to correct execution errors.

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models

BORA is an offline-to-online RL framework that enhances dexterous VLA models for real-world robotics by using an action-conditioned critic and a lightweight residual adaptation mechanism to correct execution errors.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.AIRecentMay 28, 2026

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models

Zhongxi Chen, Yifan Han, Yanming Shao, Huanming Liu +4 more

BORA is an offline-to-online RL framework that enhances dexterous VLA models for real-world robotics by using an action-conditioned critic and a lightweight residual adaptation mechanism to correct ex…

View →
cs.ROcs.AIRecentMay 28, 2026

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models

Zhongxi Chen, Yifan Han, Yanming Shao, Huanming Liu +4 more

BORA is an offline-to-online RL framework that enhances dexterous VLA models for real-world robotics by using an action-conditioned critic and a lightweight residual adaptation mechanism to correct ex…

View →