Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack

2026/06/12 by He Zhang, Lingzhu Xiang, Haitao Lin +23 · 1 citation
#cs.RO #cs.AI

paper · pdf

Abstract

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.

Citations

• Training language models to follow instructions with human feedback

Cited by

• Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

Related

• A Pragmatic VLA Foundation Model
• An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
• OpenVLA: An Open-Source Vision-Language-Action Model
• A tutorial note on collecting simulated data for vision-language-action models
• Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends