Picture for Peisong Wang

Peisong Wang

TernaryLLM: Ternarized Large Language Model

Jun 11, 2024
Viaarxiv icon

ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs

Feb 17, 2024
Viaarxiv icon

A Survey of Graph Meets Large Language Model: Progress and Future Directions

Add code
Nov 28, 2023
Figure 1 for A Survey of Graph Meets Large Language Model: Progress and Future Directions
Figure 2 for A Survey of Graph Meets Large Language Model: Progress and Future Directions
Figure 3 for A Survey of Graph Meets Large Language Model: Progress and Future Directions
Figure 4 for A Survey of Graph Meets Large Language Model: Progress and Future Directions
Viaarxiv icon

Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

Add code
Oct 20, 2022
Figure 1 for Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Figure 2 for Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Figure 3 for Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Figure 4 for Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Viaarxiv icon

Soft Threshold Ternary Networks

Add code
Apr 04, 2022
Figure 1 for Soft Threshold Ternary Networks
Figure 2 for Soft Threshold Ternary Networks
Figure 3 for Soft Threshold Ternary Networks
Figure 4 for Soft Threshold Ternary Networks
Viaarxiv icon

Differentially Private Federated Learning with Local Regularization and Sparsification

Mar 21, 2022
Figure 1 for Differentially Private Federated Learning with Local Regularization and Sparsification
Figure 2 for Differentially Private Federated Learning with Local Regularization and Sparsification
Figure 3 for Differentially Private Federated Learning with Local Regularization and Sparsification
Figure 4 for Differentially Private Federated Learning with Local Regularization and Sparsification
Viaarxiv icon

Q-ViT: Fully Differentiable Quantization for Vision Transformer

Add code
Jan 19, 2022
Figure 1 for Q-ViT: Fully Differentiable Quantization for Vision Transformer
Figure 2 for Q-ViT: Fully Differentiable Quantization for Vision Transformer
Figure 3 for Q-ViT: Fully Differentiable Quantization for Vision Transformer
Figure 4 for Q-ViT: Fully Differentiable Quantization for Vision Transformer
Viaarxiv icon

DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy

Oct 19, 2021
Figure 1 for DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
Figure 2 for DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
Figure 3 for DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
Figure 4 for DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
Viaarxiv icon

Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization

Oct 13, 2021
Figure 1 for Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
Figure 2 for Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
Figure 3 for Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
Figure 4 for Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization
Viaarxiv icon

Improving Binary Neural Networks through Fully Utilizing Latent Weights

Oct 12, 2021
Figure 1 for Improving Binary Neural Networks through Fully Utilizing Latent Weights
Figure 2 for Improving Binary Neural Networks through Fully Utilizing Latent Weights
Figure 3 for Improving Binary Neural Networks through Fully Utilizing Latent Weights
Figure 4 for Improving Binary Neural Networks through Fully Utilizing Latent Weights
Viaarxiv icon