Picture for Ziyao Wang

Ziyao Wang

SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning

Add code
Apr 23, 2024
Viaarxiv icon

FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent

Add code
Oct 06, 2023
Figure 1 for FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
Figure 2 for FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
Figure 3 for FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
Figure 4 for FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
Viaarxiv icon

A Method to Judge the Style of Classical Poetry Based on Pre-trained Model

Add code
Nov 09, 2022
Figure 1 for A Method to Judge the Style of Classical Poetry Based on Pre-trained Model
Figure 2 for A Method to Judge the Style of Classical Poetry Based on Pre-trained Model
Figure 3 for A Method to Judge the Style of Classical Poetry Based on Pre-trained Model
Figure 4 for A Method to Judge the Style of Classical Poetry Based on Pre-trained Model
Viaarxiv icon

Generation of Chinese classical poetry based on pre-trained model

Add code
Nov 04, 2022
Figure 1 for Generation of Chinese classical poetry based on pre-trained model
Figure 2 for Generation of Chinese classical poetry based on pre-trained model
Figure 3 for Generation of Chinese classical poetry based on pre-trained model
Figure 4 for Generation of Chinese classical poetry based on pre-trained model
Viaarxiv icon

A General Framework for Defending Against Backdoor Attacks via Influence Graph

Add code
Nov 29, 2021
Figure 1 for A General Framework for Defending Against Backdoor Attacks via Influence Graph
Figure 2 for A General Framework for Defending Against Backdoor Attacks via Influence Graph
Figure 3 for A General Framework for Defending Against Backdoor Attacks via Influence Graph
Figure 4 for A General Framework for Defending Against Backdoor Attacks via Influence Graph
Viaarxiv icon

Learning from Incomplete Data by Simultaneous Training of Neural Networks and Sparse Coding

Add code
Nov 28, 2020
Figure 1 for Learning from Incomplete Data by Simultaneous Training of Neural Networks and Sparse Coding
Figure 2 for Learning from Incomplete Data by Simultaneous Training of Neural Networks and Sparse Coding
Figure 3 for Learning from Incomplete Data by Simultaneous Training of Neural Networks and Sparse Coding
Figure 4 for Learning from Incomplete Data by Simultaneous Training of Neural Networks and Sparse Coding
Viaarxiv icon