📝 Publications

• Unlearning Isn’t Deletion: Investigating Reversibility of Machine Unlearning in LLMs
  arXiv preprint: 2505.16831 • PDF
  Xiaoyu Xu, Xiang Yue, Yang Liu, Qingqing Ye, Haibo Hu, Minxin Du

• OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
  arXiv preprint: 2505.04416 • PDF
  Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu