作者位次 #4/5ICLR 2026Poster· Social Aspects / Trustworthy Machine Learning
Fairness via Independence: A General Regularization Framework for Machine Learning
Yezi Liu · Hanning Chen · Wenjun Huang · Yang Ni · Mohsen Imani
社会与人本OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yezi Liu · Hanning Chen · Wenjun Huang · Yang Ni · Mohsen Imani
Wenjun Huang · Shenghao Fu · Yian Jin · Yang Ni · Ziteng Cui · Hanning Chen · Yirui He · Yezi Liu · Sanggeon Yun · SungHeon Jeong · Ryozo Masukawa · William Youngwoo Chung · Mohsen Imani
Yezi Liu · Hanning Chen · Wenjun Huang · Yang Ni · Mohsen Imani
Large Language Models (LLMs) encode vast factual knowledge, yet their inability to selectively forget specific information hinders privacy protection, bias mitigation, and post-deployment correction. We present LoRA-based Unlearning with Negative Examples (LUNE), a lightweight framework that perf...