Kaifeng Zhang

I am a second-year Ph.D. student in computer science at Columbia University, advised by Prof. Yunzhu Li. Prior to this, I obtained my Bachelors degree from Tsinghua University (Yao Class). I am fortunate to receive mentorship from Prof. Kris Hauser during my Ph.D. study, and Prof. Xiaolong Wang, Prof. Yang Gao, Prof. Li Yi during my undergrad.

I am interested in robotics, 3D vision, physics simulation, and machine learning.

If you are interested in my work and would like to discuss research opportunity, collaboration, Ph.D. application, or anything else, feel free to contact me via email: kaifeng dot z at columbia dot edu.

Google Scholar  /  Github  /  Twitter  /  LinkedIn  /  CV

profile photo
Publications
PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos
Hanxiao Jiang, Hao-Yu Hsu, Kaifeng Zhang, Hsin-Ni Yu, Shenlong Wang, Yunzhu Li
ArXiv, 2025
website / arXiv / pdf / code

We optimize a spring-mass physics model of deformable objects and integrate the model with 3D Gaussian Splatting for real-time re-simulation with rendering.

Particle-Grid Neural Dynamics for Learning Deformable Object Models from Depth Images
Kaifeng Zhang, Baoyu Li, Kris Hauser, Yunzhu Li
Robotics: Science and Systems (RSS), 2025
paper and code coming soon

We propose a neural particle-grid model for training dynamics model with real-world sparse-view RGB-D videos, enabling high-quality future prediction and rendering.

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

We learn neural dynamics models of objects from real perception data and combine the learned model with 3D Gaussian Splatting for action-conditioned predictive rendering.

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)
website / arXiv / pdf / code

We learn a material-conditioned neural dynamics model using graph neural network to enable predictive modeling of diverse real-world objects and achieve efficient manipulation via model-based planning.

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

We achieve 4D neural implicit reconstruction from only a single-view scan using deformation and topology regularizations.

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

We propose a fully self-supervised method for category-level 6D object pose estimation by learning dense 2D-3D geometric correspondences. Our method can train on image collections without any 3D annotations.

Semantic-Aware Fine-Grained Correspondence
Yingdong Hu, Renhao Wang, Kaifeng Zhang, Yang Gao
European Conference on Computer Vision (ECCV), 2022 (Oral)
arXiv / pdf / code

We show that fusing fine-grained features learned with low-level contrastive objectives and semantic features from image-level objectives can improve SSL pretraining.


Template borrowed from Jon Barron