HuggingFace Daily Papers· Juncheng Ma, Jiaxin Li, Jiankai Tu, Bo Liang, Guodong Lv, Yufan Deng, Junzhe Tang, Liangzhu Yang, Chen Bian, Zicong Cao, Baohao Zhu, Jianxin Bi, Tengfei Yan, Yinyuan Zhang, Kewei Zhang, Xinglong Chen, Kaiqi Chen, Duomin Wang, Xiaotian Tang, Liang Tan, Li Li, Yuan Xu, Haosen Yang, Yuqi Wang, Jingfei Xia, Songyan Huang, Zhiyang Dou, Zhen Dong, Enze Xie, Tat-Seng Chua, Daquan Zhou·· 3 天前精选AI 评分85
Open-HumanScale: 开放式人类与机器人经验扩展方法
Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models
AI 导读
研究团队提出Open-HumanWAM，首个将第一人称人类视频预训练扩展至5万小时的开放方法，基于Open-HumanWAM-50K语料库开发了HumanWAM-Vanilla模型，在RoboTwin 2.0上达到92.08%成功率。
推荐理由
5万小时人类视频数据训练的具身模型达到92%成功率，人机联合训练进一步突破零样本泛化能力。
来源：HuggingFace Daily Papers · arxiv.org