임성빈(林聖彬)
Lim, Sungbin
Lim, Sungbin
Ph.D. in Mathematics,
Associate Professor
Department of Statistics
College of Political Science and Economics
Korea University
E-mail: sungbin at korea dot ac dot kr
Other Information
[DBLP] [ORCID] [OpenReview]
[MathSciNet] [Math Genealogy]
[GitHub] [Linkedin] [Facebook]
Bio
안녕하세요, 고려대학교 통계학과 임성빈 교수입니다.
Currently, I am an associate professor at the Department of Statistics at Korea University. I obtained bachelor's degrees in mathematics and political science in 2010 and a Ph.D. degree in mathematics from Korea University in 2016, under the supervision of Prof. Kyeong-Hun Kim. My early studies are mostly on analytic probability theory and stochastic partial differential equations. After graduation, I worked in the industry, at Samsung Fire and Marine Insurance as a data scientist in 2016-2017, at DeepBio as a research engineer in 2017, and at Kakao Brain as an AI scientist in 2018-2019. I joined as an assistant professor in the Artificial Intelligence Graduate School and the Department of Industrial Engineering at UNIST in 2020-2023.
Research Area & Collaboration
My recent research focuses on a Computational Statistics approach to incomplete data problems in Machine Learning (including Deep Learning) from the Trustworthy & Causal AI perspective. I am recently interested in the following topics:
Probabilistic Machine Learning:
Generative Models (NeurIPS '23, NeurIPS '23, NeurIPS '24)
Robust Learning (ICRA '18, NeurIPS '21, EACL '23, CVPR '20)
Stochastic Optimization
Bandit (NeurIPS '20 , TNNLS '22) & Reinforcement Learning (RSS '20, TR Part C '23)
Black-box Optimization (AAAI '20) & AutoML (NeurIPS '19, MICCAI '19)
Causal Learning & Machine Reasoning
Counterfactual Generation (ACML w)
Large Language Model based Causal Discovery (NeurIPS '24 CaLM Workshop)
AI for Scientific Computing and Discovery
Collaboration with LG AI Research
(Important Notice)
연구실에서는 기계학습 이론 연구를 희망하는 박사과정 학생 중 수학, 통계학, 최적화, 알고리즘, 기계학습 및 프로그래밍 적성이 매우 우수한 지원자 중 제한적으로 선발하여 집중적인 연구 지도를 합니다. 연구실 소속 없이 지도교수를 희망하는 통계학과 대학원생 분들은 KUBIG 학회원에 한하여 선발 및 지도하고 있으니 참고 바랍니다.
프로그래밍(C++, Python, Julia), 기계학습 모델링, 고성능 컴퓨팅에 숙달한 소프트웨어 개발자나 박사후 연구원은 기업 협업을 통해 공동연구 프로젝트에 참여할 수 있는 기회를 제공하고 있습니다.
현재 고려대학교 인공지능학과 김성웅 교수님과 Artificial General Intelligence Lab 을 공동지도하고 있습니다. 해당
Office Hour & Consulting Service
고려대학교 재학 중인 학부생 분들께 AMA(Ask Me Anything) 상담을 제공하고 있습니다. 링크를 통해 신청하시면 됩니다 [Link].
Selected Publications
See [Google Scholar] for other publications.
(new) On Incorporating Prior Knowledge Extracted from Pre-trained Language Models into Causal Discovery, NeurIPS Workshop on Causality and Large Models, 2024 [paper]
(new) Stochastic Optimal Control for Diffusion Bridges in Function Spaces, NeurIPS, 2024 [paper]
(new) Slice and Conquer: A Planar-to-3D Framework for Efficient Interactive Segmentation of Volumetric Images, WACV, 2024 [paper]
Score-based Generative Modeling through Stochastic Evolution Equations in Hilbert Spaces, NeurIPS (Spotlight), 2023 [paper]
Score-based Generative Models with Lévy Processes, NeurIPS (Spotlight), 2023 [paper]
Bag of Tricks for In-Distribution Calibration of Pretrained Transformers, EACL, 2023 [paper]
A Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with Drone, TR Part C (IF: 9.022), 2023 [paper]
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards, NeurIPS, 2020 [paper]
Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Network, CVPR (Oral), 2020 [video] [paper] [code]
Monte Carlo Tree Search in continuous spaces using Voronoi optimistic optimization with regret bounds, AAAI (Oral), 2020 [paper] [appendix]
Scalable Neural Architecture Search for 3D Medical Image Segmentation, MICCAI, 2019 [paper]
A Sobolev space theory for stochastic partial differential equations with time-fractional derivatives, Ann. Probab., 2019 [paper]
An Lq(Lp)-theory for the time fractional evolution equations with variable coefficients, Adv. Math., 2017 [paper]
Neural Stain-Style Transfer Learning using GAN for Histopathological Images, ACML Workshop on Machine Learning for AI Platforms, 2017 [paper]
News
Our lab students ranked 2nd on the Global Leaderboard and 1st on the Student Leaderboard at ML4CO NeurIPS 2021 Competition. [Leaderboard] [News]
Selected Presentation Slides
Causal Discovery with Generative AI [dropbox] @ DS+ Tutorial Series: AI 시대의 인과추론
Advances in Score-based Generative Models [dropbox] @ AI Frontiers Summit, 한국인공지능학회, 신진 통계학자 학술대회
Beyond Gaussian: Heavy-Tail Distributions in Machine Learning [dropbox] @ 한국인공지능학회 & NAVER 공동추계학술대회 AI Theory 세션
Automated Machine Learning for Visual Domain [dropbox] @ 한국인공지능학회 동계단기강좌 [link]
Causal Learning for AI Research [dropbox] @ 서울과학기술대학교, 고려대학교
Advanced Topics [Slide1] [Slide2] @ Principles of Deep Learning (AI502/IE408/IE511)