EgoScaler: Developing Vision-Language-Action Model from Egocentric Videos

作者：Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, Shinsuke Mori · 单位：Kyoto University, Kyoto 606-8501, Japan, National Institute of Informatics, Tokyo 101-8430, Japan, Institute of Science Tokyo, Sony Interactive Entertainment, Tokyo 108-0075, JapanContact · 会议/期刊：arXiv preprint 2025 · 方向：互联网/跨域数据 · 发布日期：2025-09-26