Minhyuk Seo

I'm a Research Associate in ESAT-PSI Lab at KU Leuven, advised by Prof. Tinne Tuytelaars. My research focuses on continual learning, embodied AI and federated learning.

During my M.S., I was fortunate to work as a research intern at the Advanced Machine Learning team in LG AI research (2023).

I received my M.S. degree in Computer Science at Yonsei University under the supervision of Prof. Jonghyun Choi and B.S. degree in Computer Science from the same university.

CV / Email / Google Scholar / DBLP / Github

News

2025.04 One paper on heterogeneous federated learning for MLLMs is accepted at the CVPRW 2025 @ MMFM.

2025.03 I started as a Research Associate at KU Leuven under the supervision of Prof. Tinne Tuytelaars

2025.01 One paper on efficient continual learning is accepted at ICLR 2025 (Spotlight Presentation)

2024.09 I am invited to give a talk in Naver Labs - Recent research on continual learning

2024.06 Two papers are accepted at CoLLAs 2024 Workshop Tack

2024.06 I am invited to give a talk in Apple research - Practical set‐ups and methods for continual learning

2024.02 One paper on online continual learning is accepted at CVPR 2024

2024.01 One paper on lifelong learning agent is accepted at ICLR 2024

Work Experience

	KU Leuven Researcher at ESAT-PSI Lab (Feb. 2025 ~ Current) Advisor: Prof. Tinne Tuytelaars
	Seoul National University Researcher at SNUMPR Lab (Sep. 2024 ~ Feb. 2025) Advisor: Prof. Jonghyun Choi
	LG AI Research Research Intern at AML Team (Feb. 2023 ~ Aug. 2023) Mentor: Hankook Lee

Publications

	HEFT: Multi-modal Personalized Federated Continual Learning for Heterogeneous Clients Minhyuk Seo, Taeheon Kim, Hankook Lee, Jonghyun Choi, Tinne Tuytelaars CVPRW 2025 @ MMFM (Work in Progress)
	Just Say the Name: Online Continual Learning with Category Names Only via Data Generation Minhyuk Seo, Seongwon Cho, Minjae Lee, Diganta Misra, Hyeonbeom Choi, Seon Joo Kim, Jonghyun Choi, arXiv (Under Review) [pdf] [bibtex]
	Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling Minhyuk Seo, Hyunseo Koh, Jonghyun Choi, ICLR 2025 (Spotlight Presentation) [pdf] [bibtex]
	Learning Equi-angular Representations for Online Continual Learning Minhyuk Seo Hyunseo Koh, Wonje Jeung, Min Jae Lee, San Kim, Hankook Lee, Sungjun Cho, Sungik Choi, Hyunwoo Kim, Jonghyun Choi, CVPR 2024 [pdf] [bibtex] [code]
	Online Continual Learning for Interactive Instruction Following Agents Byeonghwi Kim, Minhyuk Seo, Jonghyun Choi ICLR 2024** [pdf] [bibtex] [code]
	Online Boundary-Free Continual Learning by Scheduled Data Prior Hyunseo Koh, Minhyuk Seo, Jihwan Bang, Hwanjun Song, Deokki Hong, Seulki Park, Jung-Woo Ha, Jonghyun Choi ICLR 2023 [pdf] [bibtex] [code]

Awards

2st Place Award - Class-Incremental with Repetition Scenario Challenge - CLVISION Workshop @ CVPR 2024
Bronze Prize - Outstanding Paper Awards - IPIU 2024
1st Place Award - Continual Test-time Adaptation for Object Detection Challenge - VCL Workshop @ ICCV 2023
1st Place Award (Minister of Science, ICT and Future Planning Award) - HANIUM ICT competition 2019

Scholarships

Kwanjeong Educational Foundation Scholarship for Graduate Student
- Full tuition and stipend of $ 9,000 per year
- Mar 2023 — Aug 2024
Yonsei Bachelor & Master Program Scholarship
- Full tuition of $ 10,000 per year
- Select two students from the department each year)
- Mar 2023 — Aug 2024
Kwanjeong Educational Foundation Scholarship for Bachelor’s program
- Full tuition and stipend of $ 8,000 per year
- Mar 2021 — Feb 2023
KB Talent Development Scholarship
- Stipend of $ 2,200
- Jan 2022 — Dec 2022
Sejong Human resources and Lifelong Education Development Foundation
- Stipend of $ 1,500
- Jul 2021 — Dec 2021

Academic Services (Reviewer)

NeurIPS Benchmark Track NeurIPS (2024), CVPR (2024-2025), ICLR (2024-2025), TPAMI (2024 - 2025), NeurIPS (2024-2025), ICML (2024-2025), ICCV (2025), AISTATS (2025), ICRA (2025), CoRL @ LLHomeRobots2024

This template is from Jon Barron.