Kun Xu

Email: kunxu dot thu at gmail dot com

I am currently a Ph.D. candidate at TSAIL Group in Department of Computer Science and Technology at Tsinghua University, advised by Prof. Jun Zhu and Prof. Bo Zhang. I also obtained my Bachelor of Engineering degree in Tsinghua University, majored in automation.

My research interests include deep learning algorithms and applications, especially the intersection of deep learning and statistical machine learning methods. I develop learning methods for GANs to improve the mode coverage and training stability. I also work on the robustness of deep neural nets. Currently, I am looking for a challenging job related to machine learning.

Publications (* denotes equal contribution.)

  • Understanding and Stabilizing GANs' Training Dynamics with Control Theory
    Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang
    International Conference on Machine Learning (ICML), 2020
  • Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks
    Tianyu Pang*, Kun Xu*, Jun Zhu
    International Conference on Learning Representations (ICLR), 2020
  • Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
    Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, Jun Zhu
    International Conference on Learning Representations (ICLR), 2020
  • To Relieve Your Headache of Training an MRF, Take AdVIL
    Chongxuan Li, Chao Du, Kun Xu, Max Welling, Jun Zhu, Bo Zhang
    International Conference on Learning Representations (ICLR), 2020
  • Learning Implicit Generative Models by Teaching Explicit Ones
    Kun Xu*, Chao Du*, Chongxuan Li, Jun Zhu, Bo Zhang
    European Conference on Machine Learning (ECML/PKDD), 2020
  • Multi-objects Generation with Amortized Structural Regularization
    Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang
    Advances in Neural Information Processing Systems (NeurIPS), 2019
  • Improving Adversarial Robustness via Promoting Ensemble Diversity
    Tianyu Pang, Kun Xu, Chao Du, Ning Chen, Jun Zhu
    International Conference on Machine Learning (ICML), 2019
  • Triple Generative Adversarial Nets
    Chongxuan Li, Kun Xu, Jun Zhu, Bo Zhang
    Advances in Neural Information Processing Systems (NeurIPS), 2017

Workshop Papers

  • Deep Structured Generative Models
    Kun Xu*, Haoyu Liang*, Jun Zhu, Bo Zhang
    International Conference on Machine Learning (ICML), Workshop on Theoretical Foundations and Applications of Deep Generative Models, 2018
  • The Youtube-8M kaggle competition: challenges and methods
    Haosheng Zhou*, Kun Xu*, Jialian Li, Jun Zhu
    Computer Vision and Pattern Recognition (CVPR), Workshop on YouTube-8M Large-Scale Video Understanding, 2017
  • Neuron Segmentation based on CNN with Semi-supervised Regularization
    Kun Xu, Hang Su, Jun Zhu, Jisong Guan, Bo Zhang
    Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016

Preprints

Contact Me

Email: kunxu dot thu at gmail dot com