Taeheon Kim
Scholar

Taeheon Kim

Google Scholar ID: VSYbxlcAAAAJ
Seoul National University
continual learningmachine learningai safety
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
26
 
H-index
3
 
i10-index
1
 
Publications
6
 
Co-authors
0
 
Contact
Emailthkim0305@snu.ac.krCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
9 items
AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoring
2026
Cited
0
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
2026
Cited
0
OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation
arXiv.org · 2026
Cited
0
Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
2025
Cited
0
TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions
2025
Cited
0
Not All Clients Are Equal: Personalized Federated Learning on Heterogeneous Multi-Modal Clients
arXiv.org · 2025
Cited
0
Representation Bending for Large Language Model Safety
2025
Cited
0
An Information Theoretic Evaluation Metric For Strong Unlearning
2024
Cited
5
Resume (English only)
Background
  • Research interests include efficient learning, continual learning, federated learning, model safety, and machine unlearning.
Miscellany
  • This template is from Jon Barron.
Co-authors
0 total
Co-authors: 0 (list not available)