Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation
where it significantly outperforms prior state-of-the-art methods.Furthermore, we demonstrate its effectiveness and robustness through real-world robot experiments.
Authors
- Yiquan Li
- Jiyue Zhu (ORCID: https://orcid.org/0000-0003-2171-0725)
- Jianglong Ye (ORCID: https://orcid.org/0000-0003-1347-9199)
- Yuzhe Qin (ORCID: https://orcid.org/0000-0002-9321-9305)
- Ruihan Yang (ORCID: https://orcid.org/0000-0003-3154-4150)
- Chengjie Yuan
- Xiaolong Wang (ORCID: https://orcid.org/0000-0001-9003-4252)
- Keyi Wang (ORCID: https://orcid.org/0000-0001-8577-0554)
- Xueyan Zou
Institutions
- UC San Diego Health System (US)
Publication Details
- Published
- 2025-06-21
- DOI
- https://doi.org/10.15607/rss.2025.xxi.106
- Citations
- 1
- Primary Topic
- Robot Manipulation and Learning
- Type
- article
- Field-Weighted Citation Impact
- 1.21