IEEE

Federated Learning With Automated Dual-Level Hyperparameter Tuning

Abstract: Federated Learning (FL) is a decentralized machine learning (ML) approach where multiple clients collaboratively train a shared model over several update rounds without exchanging local data ...
IEEE

Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective

Abstract: Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem.
GitHub

ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

To fully reproduce our experiments, please refer to ReproduceExps.md. To download our training data and reproduce the plots in the paper, please refer to ...