Dongwoo Kim
Associate Professor
Pohang-si, North Gyeongsang, South Korea
Summary
👤
Senior🎓
Top SchoolDongwoo Kim is an associate professor at POSTECH with 12 years of experience building and researching machine learning and Bayesian inference methods for large-scale data and media analysis. He earned his PhD and MS from KAIST and has held research and teaching roles at ANU and Microsoft Research, bridging academic rigor with practical system-building. His open-source work includes implementing diverse topic models—such as supervised topic models, variational Bayes S-LDA, and hierarchical Dirichlet scaling—in a public Python repository, reflecting a hands-on approach to probabilistic model development. Dongwoo's research blends statistical depth with scalable algorithms, often focusing on interpretable models for text and media; less obvious is his continuity in evolving topic-model toolchains from academic prototypes to usable code.
12 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Computer Science, Doctor of Philosophy (Ph.D.), Computer Science at KAISTBachelor's degree, Computer Engineering, Bachelor's degree, Computer Engineering at 성균관대학교 / Sungkyunkwan University
Korean, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
machine-learning10
topic-modeling10
python10
algorithms9
data-analysis8
nlp6
natural-language-processing6
scikit-learn5
scikit5
Programming languages (5)
Github contributions (5)
dongwookim-ml/python-topic-model
Aug 2014 - May 2016
Implementation of various topic models
Role in this project:
Data Scientist
Data ScientistContributions:62 commits, 10 PRs, 33 pushes in 1 year 8 months
Contributions summary:Dongwoo's primary contribution appears to be the implementation of various topic models within the repository. They began with an initial commit that introduced four different topic models. Subsequent commits added a supervised topic model (STM) based on stochastic EM and a variational Bayes (VB) implementation of supervised LDA, and also added a hierarchical Dirichlet scaling process (HDSP) model, demonstrating a focus on model development and expansion.
nlpnatural-language-processingmachine-learningtopic-models
dongwookim-ml/almc
Aug 2015 - May 2018
Contributions:271 commits, 1 PR, 209 pushes in 2 years 9 months
active-learningmachine-learninglearning-algorithmsmatrixcompletion
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.