AI+Math Lab @ Korea


In AIML@K, we expand the frontier of artificial intelligence with mathematics through researching, teaching, and outreaching for the human race.

Meet the AIMLers

Latest News

Jun 11, 2025
ICML 2025: One Main Track Paper and Four Workshop Papers Accepted
ICML 2025: One Main Track Paper and Four Workshop Papers Accepted

🎉🎉🎉🎉🎉 AIML@K members are presenting one main track paper and four workshop papers in ICML 2025! Congratulations!

Mar 2, 2025
Three AIML@K Students Appointed as TAs for the University-wide Python Course GECT 002
Three AIML@K Students Appointed as TAs for the University-wide Python Course GECT 002

We are proud to announce that three students from AIML@K have been selected as Teaching Assistants (TAs) for the university-wide introductory Python programming course “Software Programming Basics” (SW프로그래밍의 기초).

Feb 25, 2025
Two New Masters Graduating from AIML@K!
Two New Masters Graduating from AIML@K!

TWO new masters have just graduated! Congratulations, and may the force be with you!

Dec 15, 2024
Taehun Cha Wins the First Place from Concordia Contest @ Neurips 2024
Taehun Cha Wins the First Place from Concordia Contest @ Neurips 2024

We are glad to announce that Taehun Cha won the first place in the Concordia Contest @ NeurIPS 2024! 🎉

Sep 1, 2024
Four AIML@K Students Serve as TAs for Korea University’s First University-wide Data Science and Artificial Intelligence Course
Four AIML@K Students Serve as TAs for Korea University’s First University-wide Data Science and Artificial Intelligence Course

We are proud to announce that four AIML@K students are selected in the inaugural recruitment of highly skilled teaching assistants (TAs) for Korea University’s first university-wide course on Data Science and Artificial Intelligence. Selected through a rigorous university-wide recruitment process, these TAs are integral to the launch and success of this pioneering course.

See all

Select Publications

Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
Shock waves caused by earthquakes can be devastating. Generating realistic earthquake-caused ground motion waveforms help reducing …
ICML PDF
Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments
In causal inference, a randomized experiment is a de facto method to overcome various theoretical issues in observational study. …
PDF Cite DOI AAAI poster arXiv
ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments
Bypassing Stationary Points in Training Deep Learning Models
Gradient-descent-based optimizers are prone to slowdowns in training deep learning models, as stationary points are ubiquitous in the …
Cite DOI URL
Bypassing Stationary Points in Training Deep Learning Models
SentenceLDA: Discriminative and Robust Document Representation with Sentence Level Topic Model
A subtle difference in context results in totally different nuances even for lexically identical words. On the other hand, two words …
PDF Cite URL
SentenceLDA: Discriminative and Robust Document Representation with Sentence Level Topic Model
Noun-MWP: Math Word Problems Meet Noun Answers
We introduce a new type of problems for math word problem (MWP) solvers, named Noun-MWPs, whose answer is a non-numerical string …
PDF Cite URL
Noun-MWP: Math Word Problems Meet Noun Answers
See all publications