Wonje Jeung

Orcid: 0009-0008-8975-5720

According to our database1, Wonje Jeung authored at least 11 papers between 2024 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
R-TOFU: Unlearning in Large Reasoning Models.
CoRR, May, 2025

DUSK: Do Not Unlearn Shared Knowledge.
CoRR, May, 2025

SEPS: A Separability Measure for Robust Unlearning in LLMs.
CoRR, May, 2025

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment.
CoRR, May, 2025

Representation Bending for Large Language Model Safety.
CoRR, April, 2025

Representation Bending for Large Language Model Safety.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Large Language Models Still Exhibit Bias in Long Text.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios.
CoRR, 2024

An Information Theoretic Metric for Evaluating Unlearning Models.
CoRR, 2024

ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments.
Proceedings of the Computer Vision - ECCV 2024, 2024

Learning Equi-Angular Representations for Online Continual Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024


  Loading...