Brief Bio

I am an associate professor in the Graduate School of Artificial Intelligence and School of Computing at KAIST. Prior to working at KAIST, I was an assistant professor in the School of Electric and Computer Engineering at UNIST, and before that I was a postdoctoral research associate at Disney Research, working under the supervision of Professor Leonid Sigal. I did my Ph.D. in computer science at University of Texas at Austin, under the supervision of Professor Kristen Grauman. During my Ph.D. I also closely collaborated with Professor Fei Sha at University of Southern California.

I am also a co-founder of AItrics, an AI startup company located in Seoul.

Here is my (outdated) CV.

To prospective students: If you want to join our research group, contact me as early as possible, so that you can have a short-term internship before applying to the master program. If you want to do Ph.D. study under my supervision, then I recommend you to apply to the master’s program first (The master program at KAIST is an academic degree program and you will be fully supported). Our group has an opening for three master students for next year (one on computer vision, one on AutoML, and one on reinforcement learning).

I am also looking for a postdoc with strong background in deep learning, preferably with experience on retrosynthesis, speech recognition, on-device learning or real-time computer vision. Please send me your CV if you are interested.

News (6/2/2020): Four papers accepted to ICML 2020. I have 11 papers this year (4 ICML, 4 ICLR, 1 ACL, 1 AAAI and 1 ICRA).

 

Research Interests

My research interest is mainly on developing novel models and algorithms for tackling new challenges in deploying artificial intelligence systems to various real-world application domains. Regarding machine learning problems, I am mostly interested in the following topics:

  • Low-resource learning: meta-learning, network pruning & quantization, deep generative models, self- & semi-supervised learning
  • On-device learning: network pruning & quantization, continual learning, federated learning
  • Safe and secure learning: uncertainty modeling & quantification, adversarial robustness
  • Large-scale learning: meta-learning, neural architecture search, distributed & federated learning

    • The application domains of interests include but are not limited to, visual recognition, natural language understanding, speech recognition, automatic material discovery, healthcare and finance.

     

    Education

    The University of Texas at Austin, TX, USA
    Ph.D., Computer Science (Aug 2013)
    Thesis: ‘Discriminative Object Categorization with External Semantic Knowledge’

    The University of Texas at Austin, TX, USA
    M.A., Computer Science (May 2010)
    Thesis: ‘Reading Between The Lines: Object Localization Using Implicit Cues from Image Tags.’

    Seoul National University, Seoul, Korea
    B.S., Computer Science and Engineering (Feb 2008)

     

    Work

    Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea
    Associate Professor, Graduate School of AI / School of Computing (Mar 2020 ~ )
    Assistant Professor, School of Computing (Jan 2018 ~ Feb 2020)

    Ulsan National Institute of Science and Technology (UNIST), Ulsan, Korea
    Assistant Professor, School of Electric and Computer Engineering (Aug 2014 ~ Dec 2017)

    Disney Research, Pittsburgh, PA, USA
    Postdoctoral Research Associate, Computer Vision Group (Sep 2013 ~ Aug 2014)

    Microsoft Research, Redmond, WA, USA
    Research Intern, Interactive Media Group (June 2011 ~ Sep 2011)
    Mentors: Sing Bing Kang, Ashish Kapoor

    SK Communications (Formerly EMPAS), Seoul, Korea
    Lead Staff, Search Department (May 2005 ~ Jan 2007)

     

    Professional Service

    Area Chair & Senior Program Committee

    IJCAI 2021 (Area Chair)
    ICLR 2021 (Area Chair)
    ACML 2020 (Area Chair)
    ICML 2020 (Area Chair)
    IJCAI 2020 (Senior Program Committee)
    AAAI 2020 (Senior Program Committee)

    Reviewer & Program Committee

    I am a regular program committee member (or a reviewer) for the following journals and conferences:
    IEEE Transactions on Pattern Analysis and Machine Intelligence, NIPS, ICML, ICLR, IJCAI, AAAI, CVPR, ICCV, ECCV, UAI, AISTATS.

    I also (less frequently) review for the following journals/conferences:
    IEEE Transactions on Multimedia, Neural Networks, ACL, SIGGRAPH, SIGGRAPH ASIA, ACCV, EG

     

    Contact

    Office: E3-1 1427
    KAIST School of Computing
    291 Daehak-ro, Yuseong-gu, Daejeon, Korea 34141
    Email: sjhwang82 at kaist dot ac dot kr