Zexi Li

MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization

Improving Group Connectivity for Generalization of Federated Deep Learning