2 papers
cs.LG2025
GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
Peizhi Niu, Evelyn Ma, Huiting Zhou +4
Unlearning in large language models is becoming increasingly important due to regulatory compliance, copyright protection, and privacy concerns. However, a key challenge in LLM unl…
cs.LG2024
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
Evelyn Ma, Chao Pan, Rasoul Etesami +2
The performance of Transfer Learning (TL) heavily relies on effective pretraining, which demands large datasets and substantial computational resources. As a result, executing TL i…