Awesome Robotics Manipulation · full_paper

DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA

作者：Yi Chen, Yuying Ge, Hui Zhou, Mingyu Ding, Yixiao Ge, Xihui Liu · 单位：The University of Hong Kong, University of North Carolina at Chapel Hill · 会议/期刊：arXiv · 日期：2026-03-31 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Structured Vision Language Action Models

视觉语言动作潜变量学习世界模型机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA figure
AlphaXiv 中文论文页面（可滚动查看）