Scholar
Taywon Min
Google Scholar ID: CpxEc9kAAAAJ
KAIST
AI alignment
AI interpretability
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
38
H-index
2
i10-index
1
Publications
3
Co-authors
0
Contact
GitHub
Open ↗
Publications
5 items
Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning
2026
Cited
0
Entropy-Aware On-Policy Distillation of Language Models
2026
Cited
0
Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
2025
Cited
0
Understanding Impact of Human Feedback via Influence Functions
2025
Cited
0
Benchmarking Mobile Device Control Agents across Diverse Configurations
arXiv.org · 2024
Cited
16
Resume (English only)
Academic Achievements
[C2] 'Understanding Impact of Human Feedback via Influence Functions', ACL 2025, first author.
[C1] 'Benchmarking mobile device control agents across diverse configuration', CoLLAs 2025 (GenAI4DM Workshop @ ICLR 2024, Spotlight), second author.
[P1] 'Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning', under review, second author.
[P2] 'Mitigating Unintentional Misalignment of LLM Agents via Prefix Injection Guard', under review, co-first author.
Conference reviewer for ICLR 2025.
Presidential Science Scholarship, Korea Student Aid Foundation (2018–2024).
Dean's List, Seoul National University (Spring 2019, Spring 2022).
Statistic Korea's Annual Call for Research Papers and Awards (2022).
Talent Award Korea, Korea Student Aid Foundation (2017).
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up