Xueyi Liu

I am a first-year Ph.D. student in the IIIS at Tsinghua University, advised by Prof. Li Yi. Previously, I obtained my bachelor's degree in Computer Science from the CS Department, THU. My research interests center around computer vision, graphics, and embodied AI.

Email  /  Github  /  Google Scholar /  Twitter

profile photo
Research
QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer
Xueyi Liu, Kangbo Lyu, Jieqiong Zhang, Tao Du, Li Yi
ECCV, 2024
project page / code / 🤗demo / arXiv / video / slides

TL;DR: QuasiSim presents a parameterized family of quasi-physical simulators and a physics curriculum programmed from that family for transferring kinematics-only human manipulation demonstrations to dexterous robot hand simulations.

GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
Xueyi Liu and Li Yi
ICLR, 2024
project page / code / 🤗demo / arXiv / video / slides / poster

TL;DR: Generalizable HOI denoising model.

Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation
Xueyi Liu, Bin Wang, He Wang, Li Yi
ICCV, 2023
project page / code / arXiv / video / slides

TL;DR: Few-shot articulated object generation via hierarchical deformation.

Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
Xueyi Liu, Ji Zhang, Ruizhen Hu, Haibin Huang, He Wang, Li Yi
ICLR, 2023
project page / code / arXiv / video / media (in Chinese)

TL;DR: Part-level SE(3) equivariance for self-supervised articulated object pose estimation.

AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation
Xueyi Liu, Xiaomeng Xu, Anyi Rao, Chuang Gan, Li Yi
CVPR, 2022
project page / code / arXiv / video

TL;DR: Search for intermediate supervisions to improve the generalizability of part segmentation networks.

Similarity-aware Positive Instance Sampling for Graph Contrastive Pre-training
Xueyi Liu, Yu Rong, Tingyang Xu, Fuchun Sun, Wenbing Huang, Junzhou Huang
code / arXiv

TL;DR: Sample positive instances from a hierarchical graph encoding graph instance similarities for graph contrastive learning.

Network representation learning: A macro and micro view
Xueyi Liu and Jie Tang
AI Open, 2021
arXiv

TL;DR: A comprehensive survey on graph representation learning.

Understanding WeChat User Preferences and “Wow” Diffusion
Fanjin Zhang, Jie Tang, Xueyi Liu, Zhenyu Hou, Yuxiao Dong, Jing Zhang, Xiao Liu, Ruobing Xie, Kai Zhuang, Xu Zhang, Leyu Lin, Philip S. Yu
TKDE, 2021
arXiv

TL;DR: Predict WeChat users' click and ``wow'' behaviours.


Honors/Awards

  • Outstanding Bachelor Thesis of Tsinghua University, 2023
  • Outstanding Graduate of Tsinghua University, 2023
  • Comprehensive Excellence Scholarship, 2020,2021
  • Academic Excellence Scholarship, 2022
  • Services
    Reviewer: ICML, ICLR, NeurIPS, CVPR, ICCV, ECCV, ACM TIST


    Template stolen from Jon Barron. Thanks for stopping by :)
    Last updated: July, 2024