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
[C8] Building Comparative Motivation Profiles with Instrumental Interventions
David Vella Zarb*, Rustem Turtayev*, Taywon Min*, Jinghua Ou, Shi Feng
NeurIPS 2026
[C6] Entropy-Aware On-Policy Distillation of Language Models
Woogyeol Jin, Taywon Min, Yongjin Yang, Dennis Wei, Yi Zhou, Swanand Ravindra Kadhe, Nathalie Baracaldo, Kimin Lee
ICML 2026
[C5] Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning
Haeone Lee, Taywon Min, Junsu Kim, Sinjae Kang, Fangchen Liu, Lerrel Pinto, Kimin Lee
ICRA 2026
[C3] Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
Dongyoon Hahm*, Taywon Min*, Woogyeol Jin*, Kimin Lee
AAAI 2026 (AI Alignment Track)
[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 Configurations
Juyong Lee, Taywon Min, Minyong An, Dongyoon Hahm, Haeone Lee, Chanyoung Kim, Kimin Lee
CoLLAs 2025 & GenAI4DM Workshop @ ICLR 2024 (Spotlight)
[C8] Building Comparative Motivation Profiles with Instrumental Interventions
David Vella Zarb*, Rustem Turtayev*, Taywon Min*, Jinghua Ou, Shi Feng
NeurIPS 2026
[C7] Capability Provenance in Language Models: A Case Study in Social Reasoning
Glenn Matlin, Chandreyi Chakraborty, Saehee Eom, Mika Okamoto, Rayan Castilla, Louis Jaburi, Alvin Deng, Taywon Min, Lucia Quirke, Stella Biderman, Mark Riedl
COLM 2026
[C6] Entropy-Aware On-Policy Distillation of Language Models
Woogyeol Jin, Taywon Min, Yongjin Yang, Dennis Wei, Yi Zhou, Swanand Ravindra Kadhe, Nathalie Baracaldo, Kimin Lee
ICML 2026
[C5] Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning
Haeone Lee, Taywon Min, Junsu Kim, Sinjae Kang, Fangchen Liu, Lerrel Pinto, Kimin Lee
ICRA 2026
[C4] State Your Intention to Steer Your Attention: An AI Assistant for Intentional Digital Living
Juheon Choi, Juyong Lee, Jian Kim, Chanyoung Kim, Taywon Min, W. Bradley Knox, Min Kyung Lee, Kimin Lee
CHI 2026
[C3] Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
Dongyoon Hahm*, Taywon Min*, Woogyeol Jin*, Kimin Lee
AAAI 2026 (AI Alignment Track)
[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 Configurations
Juyong Lee, Taywon Min, Minyong An, Dongyoon Hahm, Haeone Lee, Chanyoung Kim, Kimin Lee
CoLLAs 2025 & GenAI4DM Workshop @ 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
Experience
Scholar (won the ARENA 6.0 hackathon)Sep. 2025
ARENA 6.0ScholarJan. 2026 - Oct. 2026
MATS 9.0 & 9.1Academic Services
Conference Reviewer, ICLR 2025, 2026
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