8 citations · 12 across the 7 of their papers we have counts for
7 papers
Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
Zexi Li, Xiangzhu Wang, William F. Shen +5
Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modif…
Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization
Zexi Li, Lingzhi Gao, Chao Wu
Generative artificial intelligence (GenAI) has made significant progress in understanding world knowledge and generating content from human languages across various modalities, lik…
Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
Didi Zhu, Zhongyi Sun, Zexi Li +5
Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a sig…
FedGuCci: Making Local Models More Connected in Landscape for Federated Learning
Zexi Li, Jie Lin, Zhiqi Li +5
Federated learning (FL) involves multiple heterogeneous clients collaboratively training a global model via iterative local updates and model fusion. The generalization of FL's glo…
Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors
Zexi Li, Zhiqi Li, Jie Lin +5
Model fusion aims to integrate several deep neural network (DNN) models' knowledge into one by fusing parameters, and it has promising applications, such as improving the generaliz…
FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning
Lingzhi Gao, Zexi Li, Yang Lu +1
Personalized federated learning (pFL) enables collaborative training among multiple clients to enhance the capability of customized local models. In pFL, clients may have heterogen…
FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks
Lingzhi Gao, Zhenyuan Zhang, Chao Wu
While existing federated learning approaches primarily focus on aggregating local models to construct a global model, in realistic settings, some clients may be reluctant to share…