Scholar
Wonje Jeung
Google Scholar ID: o6YVUQcAAAAJ
Yonsei University, Seoul National University
Privacy
Safety
Human-Centered AI
Language Models
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
80
H-index
5
i10-index
4
Publications
13
Co-authors
0
Publications
15 items
Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models
2026
Cited
0
VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
2026
Cited
0
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
2026
Cited
0
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
2026
Cited
0
Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
2026
Cited
0
Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
2025
Cited
0
A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
2025
Cited
0
DUSK: Do Not Unlearn Shared Knowledge
2025
Cited
0
Load more
