Junkang Liu

Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models

FedMuon: Accelerating Federated Learning with Matrix Orthogonalization

LAVA: A UNIFIED FRAMEWORK FOR FINETUNING LANGUAGE AND VISION MODELS

Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions

Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging