Yingdong Hu

Yingdong Hu is a PhD student at Tsinghua University affiliated with the Institute for Interdisciplinary Information Sciences, where his research focuses on robot learning, computer vision, and representation learning. He is best known for his work on vision-language-action models, including OneTwoVLA, and on data scaling laws in imitation learning for robotic manipulation. His publications also include studies on pre-trained vision models in motor control and humanoid manipulation interfaces.