Developed ThinShellLab, a differentiable physics simulation platform for diverse thin-shell materials with a set of manipulation tasks and inverse design tasks to boost robot skill acquiring on thin-shell manipulation.
Involved in RoboGen, a fully automatic pipeline to generate task, scene configuration, training supervision and learn diverse skills.
Research Intern
Peking University
01.2021 - 03.2023
Advised by Prof. Hao Dong
Under the guidance of Dr. Kaichun Mo, Dr. Ruihai Wu, Dr. Qingnan Fan and Prof. Leonidas J.Guibas
Involved VAT-Mart, a framework to predict visual action affordance and long-term trajectories for 3D articulated objects manipulation.
Developed AdaAfford, a framework that learns to perform very few test-time interactions for quickly adapting the affordance priors by eliminating the dynamic and kinematic uncertainties.
Developed Coarse-to-Fine Affordance that mitigate the effect of point cloud noise of real-sense camera by automatically choose a closer view.
Education
Computer Science Ph.D. program -
University of Massachusetts Amherst
01.2024
Bachelor of Intelligent Science and Technology -
Peking University
07.2023
Honors And Awards
SenseTime Scholarship
Li Yanhong Scholarship in Peking University 2021-2022 (ranking 1/60)
Pexpertmaker to Merit Student 2021-2022 (ranking 1/60)
Benz Scholarship in Peking University 2020-2021 (ranking 5/59)
Lee Wai Wing Scholarship in Peking University 2019-2020 (ranking 4/44)
Merit Student in Peking University 2019-2020 and 2020-2021
Second class prize in PKU-CPC 2021
Silver medal in National Olympiad in Informatics (NOI), China Computer Federation, 2018
Publications
VAT-mart: Learning visual action trajectory proposals for manipulating 3d ARTiculated objects, Ruihai Wu , Yan Zhao , Kaichun Mo , Zizheng Guo, Yian Wang, Tianhao Wu, Qingnan Fan, Xuelin Chen, Leonidas Guibas, and Hao Dong, International Conference on Learning Representations, 2022
AdaAfford: Learning to adapt manipulation affordance for 3d articulated objects via few-shot interactions, Yian Wang , Ruihai Wu , Kaichun Mo , Jiaqi Ke, Qingnan Fan, Leonidas Guibas, and Hao Dong, European conference on computer vision, 2022
Thin-shell Object Manipulations with Differentiable Physics Simulations, Yian Wang , Juntian Zheng , Zhehuan Chen, Zhou Xian, Gu Zhang, Chao Liu, Chuang Gan, Under review of ICLR2024
Robogen: Towards unleashing infinite data for automated robot learning via generative simulation, Yufei Wang , Zhou Xian , Feng Chen, Tsun-Hsuan Wang, Yian Wang, Katerina Fragkiadaki, Zackory Erickson, David Held, and Chuang Gan, arXiv preprint arXiv:2311.01455, 2023