👋 Hello! I’m Wonje Jeung, a second-year Master’s student in Artificial Intelligence at Yonsei University, where I am fortunate to be advised by Professor Albert No. I work on privacy leakage evaluation and safety-critical behavior in modern AI systems.

News

• November 2025: Our paper on Machine Unlearning (IDI) is accepted to AAAI 2026. See you in Singapore 🇸🇬
• September 2025: Our NeurIPS 2025 paper on preventing harmful reasoning in chain-of-thought has been accepted. See you in San Diego 🇺🇸
• August 2025: Two papers, SEPS and R-TOFU, have been accepted to EMNLP 2025. See you in Suzhou 🇨🇳
• June 2025: Gave a talk at the MLSYS group on reasoning for safety.
• May 2025: Two papers, LTF-TEST and RepBend, have been accepted to ACL 2025. See you in Austria 🇦🇹
• December 2024: Our papers on privacy auditing and long-text bias have been accepted to NeurIPS workshops. See you in Canada 🇨🇦
• July 2024: One paper on embodied instruction following has been accepted to ECCV.
• March 2024: One paper on continual learning and representation stability has been accepted to CVPR.