Yuwei Zengyuwei[dot]zeng0101 [at] gmail [dot] com |
|
About
-
Hi, I'm Yuwei, a CS PhD student at National University of Singapore, where I'm fortunate to be advised by Prof Xavier Bresson. My research is motivated by deploying robots into open-ended, unstructured environments for general and timely assistance. In particular, I'm interested in scalable, adaptive, and reusable robot skill acquisition through low-resource imitation learning and reinforcement learning.
Previously, I worked on applied research in learning for robot manipulation at Dyson robotics research, where I was fortunate to have worked with a team of passionate roboticists and Dr. Edward Johns. I have also worked on a series of interesting real-life deep learning solutions as an R&D engineer at Panasonic R&D Center Singapore. Before that, I obtained my bachelor's degree from Nanyang Technological University, with my thesis supervised by Prof Justin Dauwels.
Publication
-
Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
-
-
Diff-lfd: Contact-Aware Model-Based Learning from Visual Demonstration for Robotic Manipulation via Differentiable Physics-Based Simulation and Rendering
Xinghao Zhu, JingHan Ke, Zhixuan Xu, Zhixin Sun, Bizhe Bai, Jun Lv, Qingtao Liu, Yuwei Zeng, Qi Ye, Cewu Lu, Masayoshi Tomizuka, Lin Shao
CoRL 2023 (Oral)
PaperProject -
-
Learning Reward for Physical Skills using Large Language Model
Yuwei Zeng, Yiqing Xu
CoRL 2023 Workshop LangRob
PaperPosterCode -
-
ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environment
Bingyang Zhou, Haoyu Zhou, Tianhai Liang, Qiaojun Yu, Siheng Zhao, Yuwei Zeng, Jun Lv, Siyuan Luo, Qiancai Wang, Xinyuan Yu, Haonan Chen, Cewu Lu, Lin Shao
ICCV 2023
PaperProjectDataset
Projects
-
Template-Based Single-View Cloth Shape Estimation with Data-Driven Deformation Prediction and Differentiable Rendering