Awesome Robotics Manipulation · full_paper

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

作者：StarVLA Community, HKUST · 会议/期刊：arXiv · 日期：2026-04-06 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D LLM-based Vision Language Action Models

视觉语言动作语言条件机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing figure
AlphaXiv 中文论文页面（可滚动查看）