Talks & Tutorials

2026

▪︎ Aligning Vision and Language via Geometry and Topology

- KSIAM, Invited Talk

▪︎ Opportunities in IME as an AI Researcher (and Vice Versa)

- POSTECH, Graduate Seminar

2025

▪︎ Foundation Models for Vision and Language (with Code)

- Korean Statistical Society, Winter School

▪︎ Foundation Models for Vision, Language, and Robotics

- Korean Statistical Society, Tutorial

▪︎ Revisiting the 3Rs in Computer Vision

- Korea univ. (host: Prof. Sungbin Lim)

- Kyunghee univ. (host: Prof. Jinwoo Choi)

- POSTECH MINDS (host: Prof. Jae-Hun Jung)

▪︎ Scalable Priors for Foundation Models

- POSTECH (host: Prof. Minseok Song)

- UNIST (host: Prof. Jaejun Yoo)

- DGIST (host: Sunghoon Im)

Before 2025

▪︎ A Closer and Broader Look at Foundation Models

- Yonsei univ. (host: Prof. Seon-Joo Kim)

- Korea univ. (host: Prof. Jinkyu Kim)

▪︎ Foundation Models for Vision, Language, and Multimodality

- Hanyang univ. (host: Prof. Eun-Sol Kim)

▪︎ Learning Visual Representations from Uncurated Data

- Stanford (host: Prof. Jiajun Wu)

- UCSD (host: Prof. Xiaolong Wang)

- University of Michigan (host: Prof. Stella X. Yu)

▪︎ Brief History of Visual Representation Learning

- Korea univ (host: Prof. Sungbin Lim)