Siqi Song
Logo Undergraduate Student, Tsinghua University

I am currently a senior undergraduate at Department of Electronic Engineering, Tsinghua University. Previously, I had the privilege to work as an undergraduate research intern under the supervision of Prof. Yue Wang.

I am currently seeking for an Ph.D./R.A. position starting from Fall 2026. Feel free to drop me an email if you are interested in my research or have any questions.

My research interests focus on Embodied Intelligence and Robotics, in particular on the following aspects:

  • Advancing Robot-Environment-Human Interaction: With the intricate dynamics of reality, how can robots seamlessly engage in complex yet meaningful interactions with the environment and humans?
  • Learning the Embodiment and Understanding the Environment: How do robotic embodiments grasp their own physical capabilities and properties, as well as the characteristics of the surrounding environment? Furthermore, how does this knowledge shape their decision-making processes and execution strategies?
  • Reinforcement Learning and Self-Supervised Learning: How do these methodologies enhance the efficiency of learning for embodiments?

Publications (view all )
Learning from Massive Human Videos for Universal Humanoid Pose Control
Learning from Massive Human Videos for Universal Humanoid Pose Control

Jiageng Mao*, Siheng Zhao*, Siqi Song*, Tianheng Shi, Junjie Ye, Mingtong Zhang, Haoran Geng, Jitendra Malik, Vitor Guizilini, Yue Wang (* equal contribution)

Under review. 2024

We introduce Humanoid-X, a massive dataset of 20M+ robot poses with text descriptions, and UH-1, a language-driven control model - together enabling humanoid robots to effectively learn and replicate diverse human movements from video data.

Learning from Massive Human Videos for Universal Humanoid Pose Control

Jiageng Mao*, Siheng Zhao*, Siqi Song*, Tianheng Shi, Junjie Ye, Mingtong Zhang, Haoran Geng, Jitendra Malik, Vitor Guizilini, Yue Wang (* equal contribution)

Under review. 2024

We introduce Humanoid-X, a massive dataset of 20M+ robot poses with text descriptions, and UH-1, a language-driven control model - together enabling humanoid robots to effectively learn and replicate diverse human movements from video data.

All publications
Education
  • Tsinghua University
    Tsinghua University
    B.S. in Electonic Engineering
    Sep. 2021 - Present
Honors & Awards
  • Chinese National Scholarship
    2024
  • Scholarship for Comprehensive Excellence, Tsinghua University
    2023
  • Scholarship for Comprehensive Excellence, Tsinghua University
    2022