• U Jin Choi – Simulation-Free Schrodinger Bridges Via Score and Flow Matching (by Tong et al, AISTATS 2024).

    B232 Seminar Room, IBS 55 Expo-ro Yuseong-gu, Daejeon, Daejeon, Korea, Republic of

    Abstract: 임의로 정한 Initial Distribution Q1 와 Terminal Distribution Q2가 주어 졌을 때 시점과 종점 사이의 contiinious time상에  정의 되는 의미 있는 최적의 Probability Path Measure P 를 찾는 Schrodinger Bridges Problem 은 자연과학,공학, 의료 및 생명공학,경제학 및 금융공학 등의 여러 분야에 나타나는 모델들을 푸는 Unified AI Model 사용 되고 있습니다. Schrodinger Bridges Problem은  유일한 해가 존재 하는 정리는( Follmer,1988)  증명 되었으므로 데이터를 이용하여  Neural Network Models에 대한 효율적으로 학습방법,  빠른 알고리즘 연구에 집중 되고 있습니다. Tong et al 연구팀은 2023년 부터 ODE에 기반한 획기적인 생성모델인  Flow Matching for Generative Modeling 기법을  SDE 기반 Diffusion Generative Models에 접목하여 Schrodinger Bridges Problem의 해법을 제시하였습니다.

  • Jihun Han – Bridging PDEs and machine learning

    B232 Seminar Room, IBS 55 Expo-ro Yuseong-gu, Daejeon, Daejeon, Korea, Republic of

    Abstract: This talk consists of two main parts. In the first part, I will discuss a numerical method for solving PDEs based on a stochastic representation of the solution. This

  • Jae-Kwang Kim – Weight calibration for causal inference and transfer learning

    B232 Seminar Room, IBS 55 Expo-ro Yuseong-gu, Daejeon, Daejeon, Korea, Republic of

    Abstract: Weight calibration is a popular technique in handling covariate-shift problem in causal inference. It can be viewed as a dual optimization problem for incorporating the implicit regression model. We introduce the generalized entropy calibration as a general tool for weight calibration. Several interesting applications will be introduced in the context of causal inference. Furthermore, weight calibration can be used to transfer learning, which combines information from two different samples, one for source data and the other for target data.

  • Jooyoung Hahn – Topological Data Analysis with two applications: Tumor Microenvironment and 2D Chromatography with High-Resolution Mass Spectrometry

    B232 Seminar Room, IBS 55 Expo-ro Yuseong-gu, Daejeon, Daejeon, Korea, Republic of

    Abstract  Topological Data Analysis (TDA) has emerged as a powerful framework for uncovering meaningful structure in high-dimensional, complex datasets. In this talk, we present two applications of TDA in analyzing patterns, one in

  • Digital Health Care in Samsung – DongHyun Lee

    B232 Seminar Room, IBS 55 Expo-ro Yuseong-gu, Daejeon, Daejeon, Korea, Republic of

    본 발표는 삼성에서 개발 중인 디지털 헬스케어 기술을 소개합니다. 먼저, 삼성 갤럭시 웨어러블 센서의 기능과 활용 가능성을 설명하며, 웰니스 및 의료기기 서비스의 상품화 사례를 소개합니다. 또한, 삼성이 디지털 헬스케어를 통해

  • Bioinstrumentation System for Digital Health Platform: Sleep Health Monitoring Technologies Using Watch-Type Wearable – Hyunjun Jung

    B232 Seminar Room, IBS 55 Expo-ro Yuseong-gu, Daejeon, Daejeon, Korea, Republic of

    Digital health leverages information and communication technologies to transform healthcare, enabling diverse solutions for continuous health management. Among these, wearable-based digital health plays a key role by collecting, monitoring, and

  • Generative Models and Causality – Kyungwoo Song

    B232 Seminar Room, IBS 55 Expo-ro Yuseong-gu, Daejeon, Daejeon, Korea, Republic of

    This seminar examines how generative AI advances three foundational tasks in causality, treated as distinct, modular problems: (1) causal inference via intervention‑effect estimation, (2) causal graph analysis, and (3) detection