Picture for Lei Xun

Lei Xun

Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices

Add code
Jan 17, 2024
Viaarxiv icon

Fluid Dynamic DNNs for Reliable and Adaptive Distributed Inference on Edge Devices

Add code
Jan 17, 2024
Viaarxiv icon

Dynamic Transformer for Efficient Machine Translation on Embedded Devices

Add code
Jul 30, 2021
Figure 1 for Dynamic Transformer for Efficient Machine Translation on Embedded Devices
Figure 2 for Dynamic Transformer for Efficient Machine Translation on Embedded Devices
Figure 3 for Dynamic Transformer for Efficient Machine Translation on Embedded Devices
Figure 4 for Dynamic Transformer for Efficient Machine Translation on Embedded Devices
Viaarxiv icon

Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms

Add code
May 11, 2021
Figure 1 for Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms
Figure 2 for Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms
Figure 3 for Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms
Figure 4 for Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms
Viaarxiv icon

Optimising Resource Management for Embedded Machine Learning

Add code
May 08, 2021
Figure 1 for Optimising Resource Management for Embedded Machine Learning
Figure 2 for Optimising Resource Management for Embedded Machine Learning
Figure 3 for Optimising Resource Management for Embedded Machine Learning
Figure 4 for Optimising Resource Management for Embedded Machine Learning
Viaarxiv icon

Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms

Add code
May 08, 2021
Figure 1 for Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms
Figure 2 for Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms
Figure 3 for Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms
Figure 4 for Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms
Viaarxiv icon