Yang Tian

Yang Tian is a researcher affiliated with Peking University and Shanghai AI Laboratory whose work focuses on robotic manipulation and scalable robot learning. He is best known as the lead author of Seer, a Predictive Inverse Dynamics Model that achieved state-of-the-art results on the CALVIN ABC-D benchmark and was accepted as an Oral presentation at ICLR 2025. His research portfolio includes multiple publications on vision-language-action models, robotic pose estimation, and dexterous grasping.