Hwanjun Song

Hwanjun Song

Research Scientist



Currently, I am a Research Scientist at NAVER AI Lab. I graduated with my PhD in Feburary 2021 from the Graduate School of Knowledge Service Engineering at KAIST under the supervision of Prof. Jae-Gil Lee, which is leading Data Mining Lab.

Last year, I worked as a research intern at Google Research (2020 June – December) under the supervision of two hosts, Prof. Ming-Hsuan Yang and Dr. Eunyoung Kim, and two mentors, Dr. Deqing Sun and Dr. Varun Jampani.

My general research interests lie in improving the performance of machine learning techniques under real-world scenarios. I am particularly interested in designing more advanced approaches to handle large-scale and noisy data, which are two main real-world challenges to hinder the practical use of ML approaches.

In NAVER AI Lab, there are many open opsition for research internship. If you are interested in our group, please see my previous papers (especially ViDT and some works for noisy labels) and send an email to me with your CV and research interest (contact: hwanjun.song@navercorp.com)

  • Trustworthy ML
  • Large-scale ML
  • Real-world ML challenges
  • Computer Vision
  • PhD in KSE (Sep. 2016 ~ Feb. 2021)

    Korea Advanced Institute of Science and Technology (KAIST)


Research Scientist
Mar 2021 – Present
Google Research
Research Intern
Google Research
Jun 2020 – Dec 2020

2021’s Accomplish­ments

A full paper got accepted at AAAI 2022
Meta-Learning for Online Update of Recommender Systems
A full paper got accepted at AAAI 2022
Title: COVID-EENet: Predicting Fine-Grained Impact of COVID-19 on Local Economies
We propose ViDT: An Efficient and Effective Fully Transformer-based Object Detector
A full paper got accepted at BMVC 2021
Title: Exploiting Scene Depth for Object Detection with Multimodal Transformers
A full paper got accepted at KDD 2021
Title: Robust Learning by Self-Transition for Handling Noisy Labels
A tutorial proposal got accepted at KDD 2021
Title: Machine Learning Robustness, Fairness, and their Convergence
I completed to revise my Servey Paper on Noisy Labels
Title: Learning from Noisy Labels with Deep Neural Networks: A Survey
I got my PhD degree at KAIST
A full paper got accepted at AAAI 2021
Title: PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest Recommendataion