# Hy-Embodied-0.5-VLA：从视觉-语言-动作模型到真实世界机器人学习栈

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-12 08:00
- AIHOT 分数：30
- AIHOT 链接：https://aihot.virxact.com/items/cmqemsqua03peslun9wzrgxx1
- 原文链接：https://arxiv.org/abs/2606.14409

## AI 摘要

Hy-Embodied-0.5-VLA（HyVLA-0.5）是一个端到端系统，完整覆盖机器人学习栈：数据收集、模型设计、继续预训练与监督微调、强化学习后训练，以及真实世界部署。每个组件在栈中扮演独立角色。

## 正文

In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pre-training and supervised fine-tuning, RL post-training, and real-world deployment. Each component serves a distinct role in this stack.