Kaifeng Zhang

I am a second-year Ph.D. student in computer science at Columbia University, advised by Prof. Yunzhu Li. I obtained my Bachelors degree from Tsinghua University (Yao Class), where I worked with Prof. Yang Gao and Prof. Li Yi. I also interned at UC San Diego, collaborating with Prof. Xiaolong Wang. Prior to joining Columbia, I completed a year of graduate study at UIUC, where I was fortunate to collaborate with Prof. Kris Hauser.

My research is at the intersection of robotics, computer vision and machine learning. I am interested in developing robotic systems that perceive and understand the environment in a robust and generalizable manner. Currently, I explore topics including 3D reconstruction and tracking, neural dynamics model learning, and their applications to object manipulation.

Google Scholar  /  Github  /  Twitter  /  LinkedIn

profile photo
News

  • [2024.9] One paper gets accepted to CoRL 2024.
  • [2024.8] After a wonderful year at UIUC, I will be joining Columbia University to continue my PhD.
  • [2024.5] AdaptiGraph is selected as the Best Abstract Award at the 4th RMDO Workshop @ ICRA2024.
  • [2024.5] AdaptiGraph is accepted to RSS 2024.
  • [2023.8] Starting my PhD at UIUC, advised by Prof. Yunzhu Li.
  • [2023.6] Graduated from Tsinghua University.
  • [2023.1] One paper gets accepted to ICLR 2023.
  • [2022.7] One paper gets accepted to ECCV 2022.
  • Publications
    Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling
    Mingtong Zhang*, Kaifeng Zhang*, Yunzhu Li
    Conference on Robot Learning (CoRL), 2024
    website / arXiv / pdf / code / demo
    AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation
    Kaifeng Zhang*, Baoyu Li*, Kris Hauser, Yunzhu Li
    Robotics: Science and Systems (RSS), 2024
    ICRA RMDO Workshop, 2024 (Best Abstract Award, Top 1)
    website / arXiv / pdf / code
    4DRecons: 4D Neural Implicit Deformable Objects Reconstruction from a single RGB-D Camera with Geometrical and Topological Regularizations
    Xiaoyan Cong, Haitao Yang, Liyan Chen, Kaifeng Zhang, Li Yi, Chandrajit Bajaj, Qixing Huang
    Arxiv, 2024
    arXiv / pdf
    Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
    Kaifeng Zhang, Yang Fu, Shubhankar Borse, Hong Cai, Fatih Porikli, Xiaolong Wang
    International Conference on Learning Representations (ICLR), 2023
    website / arXiv / pdf / code
    Semantic-Aware Fine-Grained Correspondence
    Yingdong Hu, Renhao Wang, Kaifeng Zhang, Yang Gao
    European Conference on Computer Vision (ECCV), 2022 (Oral)
    arXiv / pdf / code
    Contact

    If you are interested in my work and would like to discuss anything, feel free to email me at: kaifeng [dot] z [at] columbia [dot] edu


    Template borrowed from Jon Barron