Awesome Robotics Manipulation · full_paper

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy

作者：Xiaokang Liu Zechen Bai Hai Ci, Kevin Yuchen Ma, VLA- RFT · 会议/期刊：arXiv · 日期：2026-02-06 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - World Model & Visual Prediction / World Model

视频规划辅助任务视觉语言动作世界模型感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy figure
AlphaXiv 中文论文页面（可滚动查看）