Weikang Wan /ˈweɪˌkɑːŋ ; wɑːn/

Email: w2wan [at] ucsd [dot] edu

Office: 5202 Atkinson Hall; 3195 Voigt Dr, La Jolla, CA 92093

I am currently a 1st-year Ph.D. student in CSE at UCSD, advised by Prof. Hao Su. Previously, I obtained my B.S. of Computer Science from Peking University with honor in 2024.

I did my research intern at Nvidia (24 Spring). I was a Visiting Student at CMU (23 Spring) and UT Austin (23 Summer).

📢 Feel free to contact me if you want to discuss or collaborate!.

[Google Scholar] [Github] [Twitter]
Research Interest

My research interest lies at the intersection of Machine Learning, Robotics, and Computer vision. I am particularly interested in developing methods to generate diverse data for robots, enabling effective learning from limited datasets.

Publications ( show selected / show all by date )
(*/†: indicates equal contribution.)
NaVid-4D: Unleashing Spatial Intelligence in Egocentric RGB-D Videos for Vision-and-Language Navigation
Haoran Liu* Weikang Wan*, Xiqian Yu*, Minghan Li*, Jiazhao Zhang, Bo Zhao, Zhibo Chen, Zhongyuan Wang, Zhizheng Zhang, He Wang

Under Review, 2024 [Paper] [Video]

DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning
Zhenyu Jiang*, Yuqi Xie*, Kevin Lin*, Zhenjia Xu, Weikang Wan, Ajay Mandlekar, Jim Fan, Yuke Zhu

Arxiv, 2024 [Project Website] [Paper]

DiffTOP: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning
Weikang Wan*, Ziyu Wang*, Yufei Wang*, Zackory Erickson, David Held

NeurIPS 2024 (Spotlight) [Project Website] [Paper] [Code]

LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery
Weikang Wan, Yifeng Zhu, Rutav Shah, Yuke Zhu

ICRA 2024 [Project Website] [Paper] [Code]

[Abridged in CoRL 2023 @ Deployable, Oral Presentation]

UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning
Weikang Wan*, Haoran Geng*, Haoran Liu*, Yun Liu, Zikang Shan, Yaodong Yang, Li Yi, He Wang

ICCV 2023 (Best Paper Finalist) [Project Website] [Paper] [Code]

Oral Presentation, Best Paper Finalist (Top 0.2% of submissions)

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
Yinzhen Xu*, Weikang Wan*, Jialiang Zhang*, Haoran Liu*, Zikang Shan, Hao Shen, Ruicheng Wang, Haoran Geng, Yijia Weng, Jiayi Chen, Tengyu Liu, Li Yi, He Wang

CVPR 2023 [Project Website] [Paper] [Code]

Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrations
Hao Shen*, Weikang Wan*, He Wang

RA-L & IROS 2022 [Project Website] [Paper] [Code]

1st place winner of SAPIEN ManiSkill Challenge 2021 (ICLR 2022 Challenge Track)

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
Yunze Liu*, Yun Liu*, Che Jiang, Kangbo Lyu, Weikang Wan, Hao Shen, Boqiang Liang, Zhoujie Fu, He Wang, Li Yi

CVPR 2022 [Project Website] [Paper] [Code]





Updated at Sep. 2024
© Weikang Wan, template from [link] and [link].