Xinqiang Yu (于新强)
Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS)
中国科学院计算技术研究所
Address: No.6 Kexueyuan South Road Zhongguancun,Haidian District Beijing,China
Email: yxq_y_x_q@163.com / 2565446948@qq.com
Currently, I am a research intern at Galbot, Led by Prof. He Wang and Dr. Zhizheng Zhang.

About me

  • I obtained my Bachelor degree from School of Software, Liaoning Technical University.
    本科 ： 辽宁工程技术大学软件学院 / 软件学院
    GPA ranking : 1/344
    I have been awarded the National Scholarship by the Ministry of Education (教育部国家奖学金) and one of the top ten university students of LNTU (校十佳大学生). During my undergraduate studies, I learned a little bit about image classification and worked with Prof. Haicheng Qu .
  • I will obtain my Master degree from Institute of Computing Technology (ICT), Chinese Academy of Sciences.
    硕士 ：中国科学院大学 / 中国科学院计算技术研究所
    Throughout my master's degree, I participated in multiple major national defense projects in the People's Republic of China.
    In the first year of master's degree, my works are mainly on Knowledge Distillation and Image Classification. And I am privileged to work closely with Prof. Chuanguang Yang. In the second year, I also focus on Reinforcement Learning. And in the last year, I mainly focus on Embodied AI. It's an honor for me to work with Prof. He Wang.

Publications

  • Jialiang Zhang*, Haoran Liu*, Danshi Li*, Xinqiang Yu*, Haoran Geng, Yufei Ding, Jiayi Chen, He Wang
    DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes
    Workshop on Dexterous Manipulation@RSS 2024
  • Xinqinag Yu, Chuanguang Yang, Chengqing Yu, Libo Huang, Zhulin An, Yongjun Xu.
    Online Policy Distillation with Decision-Attention.
    International Joint Conference on Neural Networks 2024
  • Chuanguang Yang, Xinqiang Yu, Zhulin An, Yongjun Xu.
    Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation.
    Advancements in Knowledge Distillation: Towards New Horizons of Intelligent Systems (Springer Book Chapter)
  • Chuanguang Yang, Zhulin An, Libo Huang, Junyu Bi, Xinqinag Yu, Han Yang, Boyu Diao, Yongjun Xu.
    CLIP-KD: An Empirical Study of CLIP Model Distillation.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
  • Xinqinag Yu, Chuanguang Yang, Han Yang, Libo Huang, Zhulin An, Yongjun Xu.
    Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition.
    ECCV2024 Under Review
  • Jialiang Zhang*, Haoran Liu*, Danshi Li*, Xinqiang Yu*, Haoran Geng, Yufei Ding, Jiayi Chen, He Wang
    DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes
    CoRL2024 Under Review

Research Experience

  • Galaxy Robot, Beijing, China. Oct.2023 - Now
    • Research Intern, mentored by Prof. He Wang
    • Embodied AI, Dexterous Grasping
  • Xiamen Data Intelligence Research Institute, Xiamen, China. Apr.2021 - Oct.2021
    • Research Intern in Industrial Intelligence Research Group, mentored by Neng Chen.
    • Intelligent detection of high-speed rail quality.
  • China Ordnance Industry Group, Beijing, China. Jan.2021 - May.2021

Future

  • My long-term research interest is broadly in 3D Computer Vision and Embodied AI, with particular interests in generalizable object understanding, grasping and manipulation.