arXiv preprint 2025 / 专家混合 / 其他预训练策略

Learning to See and Act: Task-Aware View Planning for Robotic Manipulation

作者：Yongjie Bai, Zhouxia Wang, Yang Liu, Kaijun Luo, Yifan Wen, Mingtong Dai, Weixing Chen, Ziliang Chen, Lingbo Liu, Guanbin Li, Liang Lin · 单位：Sun Yat-sen University, Pengcheng Laboratory, Nanyang Technological University, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, X-Era AI Lab · 会议/期刊：arXiv preprint 2025 · 方向：专家混合 / 其他预训练策略 · 发布日期：2025-08-07

视觉语言动作专家混合高效架构操作世界模型其他预训练策略高效训练
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
Learning to See and Act: Task-Aware View Planning for Robotic Manipulation figure
AlphaXiv 中文概览（可滚动查看）