Shuran Song

Stanford Professor, Diffusion Policy Creator

Profile

FieldDetails
Current PositionAssistant Professor of Electrical Engineering (by courtesy, Computer Science), Stanford University
PreviousAssistant Professor, Columbia University (2019-2023)
PhDPrinceton University (2018)
B.EngHong Kong University of Science and Technology (2013)
LabREAL@Stanford (Robotics and Embodied AI Lab)

Key Contributions

  • Diffusion Policy: Applied diffusion to robot action generation, new paradigm for VLA action generation
  • 3D Perception: 3D perception research for robotics
  • UMI (Universal Manipulation Interface): Universal data collection interface
  • Columbia to Stanford Move (2023): Strengthening robot learning research

Research Timeline

PhD & Postdoc (2013-2019)

Princeton -> Postdoc

YearWorkImpact
20153D ShapeNetsEarly 3D deep learning research
2017Semantic Scene Completion3D scene understanding
2018PhD Graduation

Columbia University (2019-2023)

CAIR Lab Founding

YearWorkImpact
2019Joined Columbia as ProfessorFounded CAIR Lab
2022Sloan Research Fellowship
2023Diffusion PolicyPioneering robot diffusion research

Stanford University (2023-present)

REAL@Stanford Founding

YearWorkImpact
2023Moved to Stanford as ProfessorFounded REAL Lab
2024UMIUniversal manipulation interface (RSS Outstanding System Paper Finalist)
2024MIT Technology Review Innovators Under 35
2025IEEE RAS Early Academic Career Award

Major Publications

Diffusion for Robotics

  • Diffusion Policy (RSS 2023, IJRR 2024) - Pioneering robot diffusion research
  • 3D Diffusion Policy (2024)

3D Perception

  • 3D ShapeNets (CVPR 2015) - Zhirong Wu, Shuran Song et al.
  • Semantic Scene Completion (CVPR 2017) - Shuran Song, Fisher Yu et al.

Robot Manipulation

  • UMI (Universal Manipulation Interface, RSS 2024) - Outstanding System Paper Finalist
  • TidyBot (Autonomous Robots 2023) - Collaboration with Andy Zeng et al.

Key Ideas

Diffusion Policy (2023)

Core: Model robot action generation as a denoising diffusion process

Noise -> ... -> Action sequence
(gradual denoising)

Advantages:
- Handling multimodal action distributions
- High training stability
- Suitable for high-dimensional action spaces

Impact:

  • Influenced pi0 (flow matching), Octo (diffusion decoder), and others
  • LeRobot default supported model
  • New paradigm for robot action generation

UMI (Universal Manipulation Interface, 2024)

Core: Universal robot data collection interface

Features:
- Applicable to various robot platforms
- Low-cost data collection
- Standardized interface

Philosophy & Direction

Research Philosophy

“3D world understanding and robot manipulation are closely connected”

Research Direction Evolution

  1. 2013-2018: 3D deep learning, scene understanding
  2. 2019-2022: 3D perception for robotics
  3. 2023-present: Diffusion for robot learning, manipulation interfaces

Key Collaborations

  • Cheng Chi: Diffusion Policy lead author, UMI collaboration
  • Toyota Research Institute: Diffusion Policy collaboration (Benjamin Burchfiel)
  • MIT: Diffusion Policy collaboration (Russ Tedrake)
  • Andy Zeng: TidyBot and other collaborations

Awards & Recognition

  • IEEE Robotics and Automation Society Early Academic Career Award (2025)
  • MIT Technology Review Innovators Under 35 (2024)
  • Samsung AI Researcher of the Year Award (2024)
  • Sloan Research Fellowship (2022)
  • NSF CAREER Award
  • Best Paper Awards: RSS 2022, T-RO 2020
  • Best System Paper Awards: CoRL 2021, RSS 2019
  • Research Awards: Microsoft, Toyota Research, Google, Amazon, JP Morgan

See Also