tencent/Hy-Embodied-0.5-VLA-Data
Dataset em destaque no Hugging Face — 68.5 mil downloads. Hy-Embodied-0.5-VLA From Vision-Language-Action Models to a Real-World Robot Learning Stack Tencent Robotics X × Tencent Hy Team 📖 Abstract We int…
O dataset tencent/Hy-Embodied-0.5-VLA-Data está entre os destaques do Hugging Face — dados que alimentam o treinamento e a avaliação dos modelos do momento.
- 68.5 mil downloads
- 11 curtidas
Sobre o dataset
Hy-Embodied-0.5-VLA From Vision-Language-Action Models to a Real-World Robot Learning Stack Tencent Robotics X × Tencent Hy Team 📖 Abstract We introduce Hy-Embodied-0.5-VLA (Hy-VLA) — an end-to-end Vision-Language-Action system that spans the full robot learning stack: data collection, model design, pre-training, supervised fine-tuning, RL post-training, and real-world deployment. Built on the Hy-Embodied-0.5 MoT backbone, Hy-VLA integrates a flow-matching… See the full description on the dataset page: https://huggingface.co/datasets/tencent/Hy-Embodied-0.5-VLA-Data.
robotics reinforcement-learning manipulation bimanual VLA leRobot lance imitation-learning
