About Me

My name is Rujie Wu, or 伍汝杰 in Chinese. You can contact me at rujie.wu.ac@gmail.com. I earned my Ph.D. at the School of Computer Science, Peking University, under the supervision of Professor Yizhou Wang. Prior to this, I earned my Master’s degree from Peking University in 2022. My primary research interests involve World Action Models and Embodied Physical AI.

🔥 News

  • 2026.07: 🎉🎉🎉 Our paper “Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning” has been accepted to ECCV 2026!

📝 Publications

ECCV 2026
sym

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

Rujie Wu, Haozhe Zhao, Hai Ci, Yizhou Wang

School of Computer Science, Peking University

ECCV 2026 | |

arXiv
sym

LongViTU: Instruction Tuning for Long-Form Video Understanding

Rujie Wu, Xiaojian Ma, Hai Ci, Yue Fan, Yuxuan Wang, Haozhe Zhao, Qing Li, Yizhou Wang

School of Computer Science, Peking University

arXiv | | |

ICCV 2025
sym

Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding

Yue Fan, Xiaojian Ma, Rongpeng Su, Jun Guo, Rujie Wu, Xi Chen, Qing Li

School of Computer Science, Peking University

ICCV 2025 | | |

NeurIPS 2024
sym

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale

Haozhe Zhao, Xiaojian Ma, Liang Chen, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li, Baobao Chang

School of Computer Science, Peking University

NeurIPS 2024 | | |

ECCV 2024
sym

Videoagent: A memory-augmented multimodal agent for video understanding

Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li

School of Computer Science, Peking University

ECCV 2024 | | |

ICLR 2024
sym

Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World

Rujie Wu, Xiaojian Ma, Zhenliang Zhang, Wei Wang, Qing Li, Song-Chun Zhu, Yizhou Wang

School of Computer Science, Peking University

ICLR 2024 | | |

ECCV 2022
sym

Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection

Hang Ye, Wentao Zhu, Chunyu Wang, Rujie Wu, Yizhou Wang

School of Computer Science, Peking University

ECCV 2022 | |

📖 Educations

sym

2022.09 - 2026.06, PhD

School of Computer Science

Peking University, Beijing

sym

2018.09 - 2022.06, Master

School of Computer Science

Peking University, Beijing