Seokil Ham
Scholar

Seokil Ham

Google Scholar ID: BXlQ2nMAAAAJ
KAIST
AI SafetyLarge Language ModelGenerative ModelEfficient Training
Google Scholar↗
Citations & Impact
All-time
Citations
29
 
H-index
3
 
i10-index
1
 
Publications
8
 
Co-authors
10
list available
Contact
No contact links provided.
Publications
3 items
Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
2026
Cited
0
Refusal-Feature-guided Teacher for Safe Finetuning via Data Filtering and Alignment Distillation
2025
Cited
0
Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
arXiv.org · 2024
Cited
0
Resume (English only)
Co-authors
10 total
Dong-Jun Han
Dong-Jun Han
Assistant Professor, Yonsei University
Co-author 2
Co-author 2
Jaekyun Moon
Jaekyun Moon
University of Minnesota, KAIST, Carnegie Mellon University
Changick Kim
Changick Kim
Korea Advanced Institute of Science and Technology
Sangmin Woo
Sangmin Woo
Amazon
Byeongjun Park
Byeongjun Park
Research Scientist at EverEx
Hyojun Go
Hyojun Go
PhD @ ETH Zurich / Google
Jin-Young Kim
Jin-Young Kim
Twelvelabs