Xiaolin Zheng

UUE: Untargeted Language Model Unlearning via Null-Space-Guided Editing with Lightweight Adapters

From One to Many: Trajectory Invariant Learning for Multimodal Large Language Model Editing

Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization

FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models

Controllable Unlearning for Image-to-Image Generative Models via $\epsilon$-Constrained Optimization

One to All: Individual Reweighting for User-Oriented Fairness in Recommender Systems