arXiv cs.RO· Renhang Liu, Wenzhi Zhao, Zhuo Yang, Liliang Chen, Pengfei Zhou, Shengcong Chen, Guanghui Ren, Youlun Peng, Rongjun Jin, Nan Wang, Sukai Wang, Xindong He, Jinyuan Feng, Ziyu Xiong, Linqing Zhong, Yifei Wei, Feng Han, Long Zhang, Da Huang, Nanshu Zhao, Chenghao Yin, Mo Wu, Zhaodong Yan, Kongtao Hu, Yuxiang Yan, Aogelijiang Niyazi, Yu Fang, Jia Zeng, Lizhu Meng, Daizhen Lv, Haoyu Cao, Zhiwen Hou, Lianjin Ye, Yuehan Niu, Zhikai Cai, Xuan Hu, Hui Min, Xiongfeng Cai, Yue Liao, Jing Wu, Soujanya Poria, Ye Li, Sanping Zhou, Maoqing Yao, AgiBot Research Team·· 1 小时前精选AI 评分77
AgiBot 团队发布 GE-Act 2.0 世界-动作模型技术报告
GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation
AI 导读
AgiBot Research Team 发布 GE-Act 2.0 世界-动作模型技术报告，其生成与动作组件全部在操作数据上从零初始化训练，由控制导向自编码器 CoAE、单步视觉规划器 SVP 和逆动力学模型 IDM 组成，并用 KASO 联合训练。
推荐理由
原文给出从零预训练世界-动作模型的组件设计与数据规模扩展曲线，可观察零样本跨本体迁移的变化。
来源：arXiv cs.RO · arxiv.org