Get started
Author

Wonje Jeung

Observed name: Jeung, Wonje
Institution: Yonsei University
ORCID: 0009-0008-8975-5720
Observed ORCID: 0009-0008-8975-5720
OpenAlex ID: A5094581156
Learning Equi-Angular Representations for Online Continual Learning
2024 · Minhyuk Seo, Hyunseo Koh, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 13
PDF
Large Language Models Still Exhibit Bias in Long Text
2025 · Wonje Jeung, Dongjae Jeon, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 7
PDF
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
2025 · Wonje Jeung, Yoon Sangyeon, et al. · neural information processing systems · 6
PDF
R-TOFU: Unlearning in Large Reasoning Models
2025 · Sangyeon Yoon, Wonje Jeung, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 6
PDF
DUSK: Do Not Unlearn Shared Knowledge
2026 · Wonje Jeung, Sangyeon Yoon, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 4
PDF
An Information Theoretic Evaluation Metric for Strong Unlearning
2026 · Dongjae Jeon, Wonje Jeung, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 3
PDF
Representation Bending for Large Language Model Safety
2025 · Ashkan Yousefpour, Taeheon Kim, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 3
PDF
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments
2024 · Taewoong Kim, Cheolhong Min, et al. · Lecture notes in computer science · 3
PDF
SEPS: A Separability Measure for Robust Unlearning in LLMs
2025 · Wonje Jeung, Sangyeon Yoon, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2
PDF
VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
2026 · Hong, Hyesoo, Kim, Min Soo, et al. · arXiv (Cornell University)
PDF
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
2026 · Yoon, Sangyeon, Jeung, Wonje, et al. · arXiv (Cornell University)
PDF
Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures
2026 · Yoon, Sangyeon, Hong, Hyesoo, et al. · arXiv (Cornell University)
PDF
An Information Theoretic Evaluation Metric for Strong Unlearning
2026 · Association for Artificial Intelligence 2026, Choi, Jonghyun, et al. · Underline Science Inc.
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
2026 · Sangyeon Yoon, Hyesoo Hong, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Same Trajectory, Contradictory Rewards (RoboRMBench): Paraphrase Fragility in Vision Language Reward Models
2026 · Wonje Jeung, Sangyeon Yoon, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
2025 · Kim, Bumjun, Jeon, Dongjae, et al. · arXiv (Cornell University)
PDF
A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
2025 · Jeung, Wonje, Yoon, Sangyeon, et al. · arXiv (Cornell University)
PDF
Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
2024 · Yoon, Sangyeon, Jeung, Wonje, et al. · arXiv (Cornell University)
PDF
Works count: 21
Citation count: 47
H-index: 4
I10-index: 1
Year
Topic
Type