Scholar
Haon Park
Google Scholar ID: a7I1fXgAAAAJ
Computer Science Student, Seoul National University
Machine Learning
Deep Learning
Image Augmentation
Robotics
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
191
H-index
3
i10-index
1
Publications
11
Co-authors
15
list available
Publications
15 items
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
2026
Cited
0
Multimodal Safety Evaluation Should Measure Controllability Beyond Classification
2026
Cited
0
EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards
2026
Cited
0
LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems
2026
Cited
0
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
2026
Cited
0
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
2026
Cited
0
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
arXiv.org · 2026
Cited
1
Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
2025
Cited
0
Load more
Co-authors
13 total
sangyoon yu
CEO, AIM Intelligence
Ashkan Yousefpour
AI Scientist
Hyunjun Kim
KAIST
Junwoo Ha
AIM Intelligence
Yuna Park
Yonsei University
Wonjun Lee
Yonsei University
Hiskias Dingeto
AIM Intelligence
Doehyeon Lee
Seoul National University
