About

I am deeply committed to advancing the field of robotics with a focus on the integration of cognitive and athletic intelligence to create robotics foundation models that could revolutionize our modern industry and society.

Please refer to my CV here

I’m currently in Tsinghua AIR working as a visiting intern in Prof. Yilun Chen’s group for dexterous policy and sim2real deployment. Before that, I work as a visiting intern in Prof. Lin Shao’s group in National University of Singapore. Before that, I was a master student at Georgia tech. Took ECE and CS courses like image processing, C++ programming, random processes, machine learning, deep learning, and robot intelligence with straight-A scores. I completed bachelors in Qingdao University with a major of Mechanical Engineering, where I did a couple of successful robot competitions for university students, and gained experience in embedded systesm, motion control, as well as computer vision, which was also the topic of my undergrad thesis.

Education & Experiences

  • Tsinghua University, Research Intern, Jan 2025-Now
  • National University of Singapore, Research Intern, June 2024-Dec 2024
  • Georgia Institute of Technology, M.Sc. ECE, Dec 2024
  • Qingdao University, B.Sc. ME, June 2021

Honors & Awards

  • National Scholarship, Ministry of Education of the People’s Republic of China, 2021
  • Nation Scholarship, Ministry of Education of the People’s Republic of China, 2019

Publication

DexSinGrap: Learning a Unified Policy for Dexterous Object Singulation and Grasping in Cluttered Environments [under-review]

Lixin Xu, Zixuan Liu, Zhewei Gui, Jingxiang Guo, Zeyu Jiang, Zhixuan Xu, Chongkai Gao, Lin Shao

website | presentation | code | arxiv

DexFlow: A Unified Approach for Dexterous Hand Pose Retargeting and Interaction [under-review]

Xiaoyi Lin, Kunpeng Yao, Lixin Xu, Xueqiang Wang, Xuetao Li, Yuchen Wang, Miao Li

website | presentation | code | arxiv

Projects

The 6th National Engineering Training Competition - Material Handling Robot

  • Embedded system (STM32) programming and design
  • Computer vision (OpenMV module, Paspberry Pi)
  • Mechanical structural design
My Image My Image

video

Monocular Depth Estimation - FADE Ain’t Depth Estimation (CS7643)

  • MiDaS and LeRes as backbone
  • Double estimation, patch estimation and Merge Net to boost performance
fade1 fade2

project paper


Attention-Based Video Inpainting Technique for Wire-Removal Scenarios (ECE6258)

  • G2L-net (Global to Local) with Transformer
  • Window-sliding Technique
My Image My Image

project paper | presentation

C++ Simulation, Games and Visualization (ECE6122)

  • CUDA-based thermal conduction simulation
  • Buzzy’s Revenge, a multimedia game based on SFML library
  • Gatech Buzzy Bowl Game, a multi-threaded 3D simulation using OpenGL
temp buzz drone

code | demo1 | demo2

ORB-based Stereo Vision Odometry

  • Designed PyVO: an ORB-SLAM inspired Python Visual Odometry
  • Recorded own dataset in dorm
My Image My Image My Image

undergrad thesis | code

Miscellaneous

Sports: skiing, hiking, biking, table tennis

I like skiing, and I went skiing 5 times this winter. I also like hiking and biking, especially in natural resorts. I’m also a table tennis player from a very young age.

Traveling: 6 countries, 21 domestic provinces

Driven by my wanderlust, I have journeyed to 6 different countries (Singapore, France, Czechia, Austria, Hungary) and 21 provinces in China.

Languages: CN, EN, DE, JP

I’m a language enthusiast. My preferred languages: Chinese (native), English (IELTS7.5/GRE322), German (roughly B1), Japanese (roughly N4), and Cantonese (beginner).

Two persons I admire the most: Geoffrey Hinton for his dedication to neural net research and Elon Musk for his aspiration and enthusiasm.