Welcome to Kuangzhi Ge's Webpage

click to continue

avatar

Kuangzhi Ge

Undergraduate Student
Peking University
gekuangzhi (at) stu.pku.edu.cn


About Me

I am a senior undergraduate student majoring in Artificial Intelligence at the School of EECS, Peking University. I am honored to be advised by Prof. Shanghang Zhang as a research intern at the HMI Lab, School of Computer Science, Peking University.

My current research interests primarily lie in multimodal learning and embodied AI, with a focus on world model. Specifically, my research interests are dedicated to exploring robust and efficient methodologies for representing world states and modeling state transitions, with the overarching goal of advancing robotic planning capabilities. I am enthusiastic about contributing to and collaborating on innovative, cutting-edge research in this field.

I am currently seeking Ph.D. opportunities starting in Fall 2026. Please feel free to contact me if you are interested in my work or potential collaboration!

Research Interests

  • Multimodal Learning: video understanding, VLM, video generation
  • Embodied AI: robot planning, VLA models, robot manipulation

Experience

  1. Peking University
    • (2022.09-Present) B.S in Computer Science
  2. HMI Lab, National Key Laboratory for Multimedia Information Processing
    • (2024.01-Present) Undergraduate Research Assistant

News🔥

  • [Sept. 2025]📃 DyVA WorldLM is released!
  • [Jun. 2025]📃 Glad to present MinD! A dual-system World Model for robot manipulation.
  • [Dec. 2024]🏅 I'm honored to be the recipient of the 1st Peking University YUNDING Scholarship.
  • [Dec. 2024]📃 Our benchmark paper on sports video commentary for video LLMs is released!


Selected Publications (Click for full list)

  1. Can World Models Benefit VLMs for World Dynamics?
    Kevin Zhang*, Kuangzhi Ge*, Xiaowei Chi*, Renrui Zhang, Shaojun Shi, Zhen Dong, Sirui Han✉, Shanghang Zhang✉
    PDF Code Project Page BibTex In submission

  2. MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis
    Xiaowei Chi*, Kuangzhi Ge*, Jiaming Liu†, Siyuan Zhou, Peidong Jia, Kevin Zhang, Yuzhen Liu, Tingguang Li, Sirui Han, Shanghang Zhang✉, Yike Guo✉
    PDF Code Project Page BibTex In submission

  3. SCBench: A Sports Commentary Benchmark for Video LLMs
    Kuangzhi Ge*, Lingjun Chen*, Kevin Zhang†, Yulin Luo, Tianyu Shi, Liaoyuan Fan, Xiang Li, Guanqun Wang, Shanghang Zhang✉
    PDF BibTex In submission

Miscellaneous

  • I held the position of President of the Student Rugby🏉 Football🏈 Association of Peking University during the 2023-2024 academic year.
  • 🏈 I serve as the defensive captain of the university’s American football team, playing as a linebacker and tight end. 🔥🔥🔥 Come see my Pick6🏈 V.S BISU Snowwolves🐺
  • 💪 I’m living on a gym lifestyle, hitting the gym at least twice a week.
  • 🎧 I love Hip-hop and R&B Music. I’m a huge fan of J.Cole, Ye and Usher.

Powered by Jekyll and Minimal Light theme.