Hyundong Jin
Scholar

Hyundong Jin

Google Scholar ID: zxUo7igAAAAJ
Ph.D candidate student in Yonsei Univ.
Language Model for CodeLanguage Model with RegexMachine LearningComputer Vision
Google Scholar↗
Citations & Impact
All-time
Citations
7
 
H-index
1
 
i10-index
0
 
Publications
3
 
Co-authors
0
 
Contact
No contact links provided.
Publications
10 items
CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders
2026
Cited
0
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
2026
Cited
0
Steering Language Models Before They Speak: Logit-Level Interventions
2026
Cited
0
How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs
arXiv.org · 2026
Cited
0
KOTOX: A Korean Toxic Dataset for Deobfuscation and Detoxification
2025
Cited
0
RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems
2025
Cited
0
Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models
2025
Cited
0
TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)