Jieming Cui

Jieming Cui

Peking University

I am currently a first-year Ph.D. student at the Institute of Artificial Intelligence at Peking University, where I'm part of both the CoRe Lab and the General Vision Lab. Additionally, I'm undertaking an internship at BIGAI under the guidance of Tengyu Liu, Siyuan Huang, and Yixin Zhu.

My research focuses on human motion generation, robotics, scene understanding, and leveraging AI for scientific discovery, particularly in the field of biology. Moving forward, my research will focus on how embodied agents can execute actions based on open-vocabulary instructions within real-world environments.

I graduated from Siyuan Class, Beijing Jiaotong Univeristy with a bachelor’s degree and from the Beihang University with a master’s degree, advised by Guizhen Yu and Yunpeng Wang.

🔥 News

  • 2024.06: Presented at CVPR workshop MANGO
  • 2024.03: 🎉 One demo is accepted by 3DV 2024 demo track
  • 2024.02: 🎉 One paper is accepted by CVPR 2024
  • 2023.09: One paper is accepted by NeurIPS 2023
  • 2023.09: Enrolled to pursue a Ph.D. degree in the field of Artificial Intelligence.
  • 2023.06: One paper is accepted by ICCV 2023

📝 Publications

CVPR 2024
sym

AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents
Jieming Cui*, Tengyu Liu*, Nian Liu*, Yaodong Yang, Yixin Zhu†, Siyuan Huang†

Project / Code / Video / Paper

We propose AnySkill, a novel hierarchical method that learns physically plausible interactions following open-vocabulary instructions. An important feature of our method is the use of image-based rewards for the high-level policy, which allows the agent to learn interactions with objects without manual reward engineering.

NeurIPS 2023
sym

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
Jieming Cui*, Ziren Gong* , Baoxiong Jia*, Siyuan Huang, Zilong Zheng†, Jianzhu Ma†, Yixin Zhu†

Project / Code / Video / Paper / 北大AI院官微

We first curate a comprehensive multimodal dataset, named ProBio, as an initial step towards monitoring system. This dataset comprises fine-grained hierarchical annotations intended for the purpose of studying activity understanding in Biology lab.

ICCV 2023
sym

Full-Body Articulated Human-Object Interaction
Nan Jiang*, Tengyu Liu*, Zhexuan Cao, Jieming Cui, He Wang, Yixin Zhu†, Siyuan Huang†

Project / Code / Paper

We present CHAIRS, a large-scale motion-captured f-AHOI dataset, consisting of 16.2 hours of versatile interactions between 46 participants and 74 articulated and rigid sittable objects. CHAIRS provides 3D meshes of both humans and articulated objects during the entire interactive process, as well as realistic and physically plausible full-body interactions.

  • ASCE 2021 Forecasting Freeway On-Ramp Lane-Changing Behavior Based on GRU, Jieming Cui*, Guizhen Yu* , Bin Zhou, Qiujun Liu, Zhengguo Guan†

  • SAE 2021 Three-Dimensional Object Detection Based on Deep Learning in Enclosed Scenario, Jieming Cui*, Guizhen Yu* , Na Zhang, Zhangyu Wang

    • 📖 Educations

    • 2023.09 - now, PhD, Peking University, Beijing.
    • 2019.09 - 2022.02, Master, Beihang University, Beijing.
    • 2015.09 - 2019.06, Undergraduate, Beijing Jiaotong University, Beijing.

    💻 Internships

    • 2022.02 - now, BIGAI, Beijing.
    • 2021.06 - 2021.09, Amap, Alibaba, Beijing.
    • 2020.02 - 2021.06, Tage Zhixing, Beijing.