Dongho Kim
M.S. in Statistics & Data Science, Northwestern University
Applying to PhD programs for Fall 2027
My research starts from one question: how do we know whether an AI system actually works for the people who use it? I'm fortunate to be advised by Prof. Han Liu in the MAGICS Lab at Northwestern, where I co-developed SPINE. I also collaborate with the NSF–Simons SkAI Institute on time-series foundation models and agents for astronomy.
Research interests
Reliable AI & sociotechnical evaluation
Evaluating AI systems in the settings where people actually use them, not only on benchmarks.
Human–AI collaboration
How people and AI systems work and decide together, and when the combination does better than either alone.
Computational social science
Studying social systems with computational methods, and increasingly with AI itself.
News
- An updated version of SPINE is on arXiv, with results on two robot platforms and a project page.
- Presented Frontier Agents for Variable-Star Analysis and Classification as a poster at Open SkAI 2026.
- Presented StarEmbed at ICML 2026; it received the Outstanding Paper Award after an oral presentation at the AI4Physics Workshop.
- Joined the NSF–Simons SkAI Institute collaboration on foundation models for astronomical time series.
- Started my M.S. at Northwestern University and joined MAGICS Lab (Prof. Han Liu).
Publications & Preprints
M. Ham*, D. Kim*, C. Lee*, M. J. Kim, Y. Zhang, J. Wang, H. Liu (*equal contribution)
StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
W. Li*, H.-Y. Chen*, N. Rehemtulla*, V. Shah, D. Kim, D. Wu, Q. Lin, A. Miller, H. Liu (*equal contribution)
Ongoing
Sci2Pol
Measuring whether LLM-based reviewers catch unsupported or overstated claims in AI-generated science-to-policy briefs.
Agentic AI for variable stars
Agents for variable-star analysis and classification, with the SkAI Institute.