ICLR 2025 / 数据增强

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

作者：Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo · 单位：Stony Brook University of Wisconsin-Madison · 会议/期刊：ICLR 2025 · 方向：数据增强 · 发布日期：2024-06-28

视觉语言动作数据增强数据采集机器人学习
新标签打开 AlphaXiv新标签打开 Code
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy figure
AlphaXiv 中文概览（可滚动查看）