Shuran Song
Shuran Song is an Assistant Professor of Electrical Engineering and, by courtesy, Computer Science at Stanford University, where she leads the Robotics and Embodied AI Lab (REAL@Stanford). Her research focuses on developing algorithms that enable intelligent systems to learn from interactions with the physical world, with interests spanning computer vision, robotics, and autonomous manipulation. She previously served on the faculty at Columbia University and earned her Ph.D. in Computer Science from Princeton University. Her work has been recognized with multiple awards including the IEEE Robotics and Automation Society Early Academic Career Award in 2025, the NSF Career Award, and a Sloan Foundation fellowship.
“The paper introduces RoboToken, a tokenization scheme that converts any articulated robot's embodiment (links, joints, motors), states, and actions into a consistent sequence of continuous-valued vectors.”
Source→“Quote: The work aims to 'explore robot morphologies as diverse as the manipulation tasks they perform, moving beyond robot hardware as a static constraint' (Section 4, Limitations).”
Source→“Senior author, director of the ROAM Lab. Creator of UMI (Universal Manipulation Interface), one of the most influential recent contributions to robot data collection.”
Source→“The handheld gripper system used to collect 76 target motion trajectories. The paper extends UMI for bimanual dishwashing demonstrations.”
Source→“Rather than maintaining separate neural networks for design generation, design evaluation, and robot control, Transformer Transformer consolidates all three into a single diffusion transformer.”
Source→“Shuran Song — Stanford University. Director of the Stanford Vision and Learning Lab. One of the most influential researchers in robot manipulation and learning. Co-author on Diffusion Policy (cited as [4]), which is the grasping policy framework used in Handroid.”
Source→“Shuran Song is a female scholar I deeply respect. Her group produced Diffusion Policy — that came from Shuran's group. And ACT and Aloha came from Chelsea's group. I think both are milestone papers that profoundly influenced the current form of machine learning for robotics.”
Source→“To our knowledge, this is the first vine robot system capable of autonomous closed-loop control using on-board sensing alone”
Source→“"In 2023, Shuran Song's lab (then at Columbia, now at Stanford) published Diffusion Policy..."”
Source→“"In 2023, Shuran Song's lab (then at Columbia, now at Stanford) published Diffusion Policy, an approach that showed end-to-end deep learning could match or beat the best hand-engineered robots on manipulation tasks."”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.