Mingdong Wu   |   吴铭东

I have been a Ph.D. student since 2021 in the School of Computer Science at Peking University, advised by Prof. Hao Dong. I received my bachelor degree in 2021, from Turing Class in Peking University.

My research interest lies in robot learning, generative models, reinforcement learning and 3D perception problems. I aim to build intelligent embodied agents that automatically discover and perform tasks without human specification.

Email  /  Google Scholar


* indicates equal contribution.

GenPose: Generative Category-level Object Pose Estimation via Diffusion Models
Jiyao Zhang*, Mingdong Wu*, Hao Dong
NeurIPS, 2023
paper link / project page / codes / bibtex

We explore a pure generative approach to tackle the multi-hypothesis issue in 6D Category-level Object Pose Estimation. The key idea is to generate pose candidates using a score-based diffusion model and filter out outliers using an energy-based diffusion model. By aggregating the remaining candidates, we can obtain a robust and high-quality output pose.

GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
Tianhao Wu*,Mingdong Wu*, Jiyao Zhang, Yunchong Gan, Hao Dong
NeurIPS, 2023
paper link / project page / codes / bibtex

Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation
Hongcheng Wang, Andy Guan Hong Chen, Xiaoqi Li, Mingdong Wu, Hao Dong
NeurIPS, 2023
paper link / project page / codes / bibtex

The First Demand-driven Navigation Paper.

Learning Gradient Fields for Scalable and Generalizable Irregular Packing
Tianyang Xue*, Mingdong Wu*, Lin Lu, Haoxuan Wang, Hao Dong, Baoquan Chen
Siggraph Asia, 2023
paper link / project page / codes / bibtex

Score-PA: Score-based 3D Part Assembly
Junfeng Cheng, Mingdong Wu, Ruiyuan Zhang, Guanqi Zhan, Chao Wu, Hao Dong
BMVC, 2023 (Oral)
paper link / codes / bibtex

Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation
Hongcheng Wang*, Yuxuan Wang*, Fangwei Zhong, Mingdong Wu, Jianwei Zhang, Yizhou Wang, Hao Dong
RAL, 2023
paper link / project page / codes / bibtex

GFPose: Learning 3D Human Pose Prior with Gradient Fields
Hai Ci, Mingdong Wu, Wentao Zhu, Xiaoxuan Ma, Hao Dong, Fangwei Zhong, Yizhou Wang
CVPR, 2023
paper link / project page / codes / bibtex

GFPose is a unified 3D human pose prior model that can be easily used for various applications, e.g., 3D human pose estimation, pose denoising and generation. Our key idea is to estimate the gradient field (a.k.a, score) of the perturbed human pose. We can leverage the gradient to adjust poses to be more plausible and feasible to a task specification.

TarGF: Learning Target Gradient Field for Object Rearrangement
Mingdong Wu*, Fangwei Zhong*, Yulong Xia, Hao Dong.
NeurIPS, 2022
paper link / project page / codes / bibtex

We study object rearrangement without explicit goal specification. The agent is given examples from a target distribution and aims at rearranging objects to increase the likelihood of the distribution. Our key idea is to learn a target gradient field that indicates the fastest direction to increase the likelihood from examples via score-matching.