Picture for Zi Yang

Zi Yang

MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization

Jun 02, 2024
Viaarxiv icon

CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization

May 23, 2024
Viaarxiv icon

Equipping Transformer with Random-Access Reading for Long-Context Understanding

May 21, 2024
Viaarxiv icon

Parameter-Efficient Fine-Tuning With Adapters

May 09, 2024
Figure 1 for Parameter-Efficient Fine-Tuning With Adapters
Figure 2 for Parameter-Efficient Fine-Tuning With Adapters
Figure 3 for Parameter-Efficient Fine-Tuning With Adapters
Figure 4 for Parameter-Efficient Fine-Tuning With Adapters
Viaarxiv icon

COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization

Add code
Mar 11, 2024
Figure 1 for COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Figure 2 for COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Figure 3 for COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Figure 4 for COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Viaarxiv icon

Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing

Jan 10, 2024
Viaarxiv icon

Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding

Jun 01, 2023
Figure 1 for Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding
Figure 2 for Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding
Figure 3 for Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding
Figure 4 for Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding
Viaarxiv icon

Leveraging Global Binary Masks for Structure Segmentation in Medical Images

May 13, 2022
Figure 1 for Leveraging Global Binary Masks for Structure Segmentation in Medical Images
Figure 2 for Leveraging Global Binary Masks for Structure Segmentation in Medical Images
Figure 3 for Leveraging Global Binary Masks for Structure Segmentation in Medical Images
Figure 4 for Leveraging Global Binary Masks for Structure Segmentation in Medical Images
Viaarxiv icon

Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior

Add code
Oct 05, 2020
Figure 1 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior
Figure 2 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior
Figure 3 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior
Figure 4 for Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior
Viaarxiv icon

Towards a Human-like Open-Domain Chatbot

Add code
Feb 27, 2020
Figure 1 for Towards a Human-like Open-Domain Chatbot
Figure 2 for Towards a Human-like Open-Domain Chatbot
Figure 3 for Towards a Human-like Open-Domain Chatbot
Figure 4 for Towards a Human-like Open-Domain Chatbot
Viaarxiv icon