Picture for Xiaohui Wang

Xiaohui Wang

Understanding Parameter Sharing in Transformers

Add code
Jun 15, 2023
Figure 1 for Understanding Parameter Sharing in Transformers
Figure 2 for Understanding Parameter Sharing in Transformers
Figure 3 for Understanding Parameter Sharing in Transformers
Figure 4 for Understanding Parameter Sharing in Transformers
Viaarxiv icon

MobileNMT: Enabling Translation in 15MB and 30ms

Add code
Jun 07, 2023
Figure 1 for MobileNMT: Enabling Translation in 15MB and 30ms
Figure 2 for MobileNMT: Enabling Translation in 15MB and 30ms
Figure 3 for MobileNMT: Enabling Translation in 15MB and 30ms
Figure 4 for MobileNMT: Enabling Translation in 15MB and 30ms
Viaarxiv icon

LightSeq2: Accelerated Training for Transformer-based Models on GPUs

Add code
Oct 27, 2021
Figure 1 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Figure 2 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Figure 3 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Figure 4 for LightSeq2: Accelerated Training for Transformer-based Models on GPUs
Viaarxiv icon

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

Add code
Oct 28, 2020
Figure 1 for LightSeq: A High Performance Inference Library for Sequence Processing and Generation
Figure 2 for LightSeq: A High Performance Inference Library for Sequence Processing and Generation
Figure 3 for LightSeq: A High Performance Inference Library for Sequence Processing and Generation
Figure 4 for LightSeq: A High Performance Inference Library for Sequence Processing and Generation
Viaarxiv icon

Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping

Add code
Jun 07, 2020
Figure 1 for Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping
Figure 2 for Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping
Figure 3 for Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping
Figure 4 for Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping
Viaarxiv icon

An Efficient Agreement Mechanism in CapsNets By Pairwise Product

Add code
Apr 01, 2020
Figure 1 for An Efficient Agreement Mechanism in CapsNets By Pairwise Product
Figure 2 for An Efficient Agreement Mechanism in CapsNets By Pairwise Product
Figure 3 for An Efficient Agreement Mechanism in CapsNets By Pairwise Product
Figure 4 for An Efficient Agreement Mechanism in CapsNets By Pairwise Product
Viaarxiv icon