Zihan Yang

Zihan Yang

Peking university

Zihan Yang

Curious Mind | Gentle but Resolute

School of Electronics Engineering and Computer Science, Peking University

About Me

I am Zihan Yang, currently a sophomore student in the Intelligent Science and Technology program (Zhi Class) at Peking University. Serving as the Vice President of the Academic Committee of Intelligence Science and Technology (ZhiXueHui).

My primary research interest lies in Embodied AI, focusing on how intelligent agents can learn and interact with physical environments through sensory-motor experiences. I believe that true intelligence emerges from the interaction between an agent and its environment, and I am excited to contribute to this rapidly evolving field.

I enjoy playing the guitar,shuttlecock kicking,playing table tennis,and chatting with people.

Research Interests

  • Vision Language Navigation
  • World Model
  • Vision Language Action Model

Latest Updates

  • 2026.4.2 - Submitted “VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments” to ACMMM2026
    Haolin Yang†, Yuxing Long†, Zihan Yang†, Hao Dong‡.[†Equal Contribution, ‡Corresponding Author]
    The first VLN instruction generation framework for continuous environments!
  • 2026.1.31 - “NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions” accepted to ICRA 2026!
  • 2025.11.8 - “CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model” accepted to AAAI 2026!
  • 2025.10.9 - Submitted “NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions” to arXiv
    Haolin Yang†, Yuxing Long†, Zhuoyuan Yu, Zihan Yang, Minghan Wang, Jiapeng Xu, Yihan Wang, Ziyan Yu, Wenzhe Cai, Lei Kang, Hao Dong‡ (2025). arXiv preprint arXiv:2510.08173. [†Equal Contribution, ‡Corresponding Author] [Paper]
  • 2025.9.22 - National Scholarship(Highest honor for undergraduates in China)
  • 2025.9.22 - Merit Student of Peking University
  • 2025.8.14 - Submitted “CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model” to arXiv
    Zhuoyuan Yu†, Yuxing Long†, Zihan Yang, Chengyan Zeng, Hongwei Fan, Jiyao Zhang, Hao Dong‡ (2025). arXiv preprint arXiv:2508.10416. [†Equal Contribution, ‡Corresponding Author] [Paper]
  • 2023.6.21 - Admitted to the School of the Gifted Young (ShaoChuang Class) at the University of Science and Technology of China (USTC).

Currently working on

  • Currently exploring research opportunities in embodied intelligence
  • Organizing academic events and seminars through the Academic Committee of Intelligence Science and Technology
  • Developing foundational skills in world model and robotics

Education

Contact