Taywon Min

Researcher

KAIST AI

taywonmin [AT] kaist.ac.kr / taywonm [AT] gmail.com

About

I am a graduate student at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. Kimin Lee. I received a B.S. degree in Statistics / interdisciplinary major in AI at Seoul National University. I am interested in AI alignment and AI safety. In past projects, I have investigated the impact of data on model performance through influence functions, and the safety degradation of fine-tuned LLM agents. My goal is to develop methods that provides safety in a scalable manner, even for large powerful models.

Publications

[P2] Mitigating Unintentional Misalignment of LLM Agents via Prefix Injection Guard

Dongyoon Hahm*, Taywon Min*, Woogyeol Jin*, Kimin Lee

under review

[P1] Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning

Haeone Lee, Taywon Min, Junsu Kim, Fangchen Liu, Lerrel Pinto, Kimin Lee

under review

[C2] Understanding Impact of Human Feedback via Influence Functions

Taywon Min, Haeone Lee, Yongchan Kwon, Kimin Lee

ACL 2025

[C1] Benchmarking mobile device control agents across diverse configuration

Juyong Lee, Taywon Min, Minyong Ahn, Dongyoon Hahm, Haeone Lee, Kimin Lee

CoLLAs 2025, GenAI4DM Workshop @ International Conference on Learning Representations (ICLR), 2024 (Spotlight)

[P2] Mitigating Unintentional Misalignment of LLM Agents via Prefix Injection Guard

Dongyoon Hahm*, Taywon Min*, Woogyeol Jin*, Kimin Lee

under review

[P1] Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning

Haeone Lee, Taywon Min, Junsu Kim, Fangchen Liu, Lerrel Pinto, Kimin Lee

under review

[C2] Understanding Impact of Human Feedback via Influence Functions

Taywon Min, Haeone Lee, Yongchan Kwon, Kimin Lee

ACL 2025

[C1] Benchmarking mobile device control agents across diverse configuration

Juyong Lee, Taywon Min, Minyong Ahn, Dongyoon Hahm, Haeone Lee, Kimin Lee

CoLLAs 2025, GenAI4DM Workshop @ International Conference on Learning Representations (ICLR), 2024 (Spotlight)

Education

Korea Advanced Institute of Science and Technology (KAIST)Mar. 2025 - Present

Graduate Student in Artificial Intelligence

Seoul National UniversityMar. 2018 - Feb. 2025

B.S. in Statistics / Interdisciplinary Major in AI

Academic Services

Conference Reviewer, ICLR 2025

Honors & Awards

Presediential Science Scholarship, Korea Student Aid Foundation2018 - 2024

Dean's List, Seoul National University2019 Spring, 2022 Spring

Statistic Korea's Annual Call for Research Papers and Awards, Statistics Korea2022

Talent Award Korea, Korea Student Aid Foundation2017