Hong Liu

PhD Student, Compuster Science, Stanford University E-mail: hliu99 [@] stanford [DOT] edu Google Scholar: https:scholar.google.com/citations?user=BUc2uq0AAAAJ

About me

I am a PhD student at Stanford University. I'm fortunate to work with Prof. Mingsheng Long and Prof. Tengyu Ma.

My current interests include transfer learning and deep learning. I have also been working on domain adaptation algorithms and their applications.
If you are also interested in this, feel free to contact me.

Publications

Conferennce Proceedings

1. Learning to Adapt to Evolving Domains
   Hong Liu, Mingsheng Long, Jianmin Wang, Yu Wang
   NeurIPS 2020
   

2. Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers
   Hong Liu, Mingsheng Long, Jianmin Wang, Michael I. Jordan
   ICML 2019, (Long Talk)
   

3. Separate to Adapt: Open Set Domain Adaptation via Progressive Separation
   Hong Liu, Zhangjie Cao, Mingsheng Long, Jianmin Wang, Qiang Yang
   CVPR 2019
   

Preprints

1. Cycle Self-Training for Domain Adaptation
   Hong Liu, Jianmin Wang, Mingsheng Long
   arxiv preprint
   

2. Towards Understanding the Transferability of Deep Feature Representations
   Hong Liu, Mingsheng Long, Jianmin Wang, Michael I. Jordan
   arxiv preprint
   

3. Meta-learning Transferable Representations with a Single Target Domain
   Hong Liu, Jeff Z. HaoChen, Colin Wei, Tengyu Ma
   arxiv preprint
   

Selected Awards and Honors

• Top Grade Schlarship, The best award for undergrads in Tsinghua

• National Scholarship, awarded for academic excellence, Ministry of Education

Professional Services

Reviewing

• Journal: TPAMI, and TIP

• Conference: ICML, NeurIPS, ICLR, and AAAI