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

Zhenyu Wei

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Robotics×3AI×1Vision×1ML×1

Frequent co-authors

Sikai Li3×
Yunchao Yao3×
Mingyu Ding3×
Chenyang Ma2×
Zhuxiu Xu2×
Dihong Huang2×

Research Timeline

2026
DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand

A framework called DexCompose is proposed to reuse pretrained dexterous policies for multi-task manipulation with explicit finger-level action ownership.

DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation

The paper introduces DexVerse, a large-scale and modular benchmark for dexterous manipulation with 100 tasks, 3 robot arms, 6 hands, and configurable visual variations.

Handroid: Bridging Dexterous Hand and Humanoid

A single robot platform, Handroid, is introduced that can function as both a dexterous hand and a humanoid robot, with interchangeable control and learning frameworks.

Highlighted terms show continued research focus across papers

Papers

cs.ROEmpiricalRecentJul 17, 2026

Handroid: Bridging Dexterous Hand and Humanoid

Ruogu Li, Chenyang Ma, Sikai Li, Zhenyu Wei +5 more

A single robot platform, Handroid, is introduced that can function as both a dexterous hand and a humanoid robot, with interchangeable control and learning frameworks.

View →
cs.ROEmpiricalRecent
Jul 9, 2026

DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation

Yunchao Yao, Zhuxiu Xu, Tianqi Zhang, Zixian Liu +11 more

The paper introduces DexVerse, a large-scale and modular benchmark for dexterous manipulation with 100 tasks, 3 robot arms, 6 hands, and configurable visual variations.

View →
cs.ROcs.AIcs.CVEmpiricalRecentJun 26, 2026

DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand

Dihong Huang, Zhenyu Wei, Zhuxiu Xu, Yunchao Yao +2 more

A framework called DexCompose is proposed to reuse pretrained dexterous policies for multi-task manipulation with explicit finger-level action ownership.

View →