Picture for Zining Zhang

Zining Zhang

Aggressive Post-Training Compression on Extremely Large Language Models

Add code
Sep 30, 2024
Viaarxiv icon

HARL: Hierarchical Adaptive Reinforcement Learning Based Auto Scheduler for Neural Networks

Add code
Nov 21, 2022
Viaarxiv icon

TransMask: A Compact and Fast Speech Separation Model Based on Transformer

Add code
Feb 19, 2021
Figure 1 for TransMask: A Compact and Fast Speech Separation Model Based on Transformer
Figure 2 for TransMask: A Compact and Fast Speech Separation Model Based on Transformer
Figure 3 for TransMask: A Compact and Fast Speech Separation Model Based on Transformer
Figure 4 for TransMask: A Compact and Fast Speech Separation Model Based on Transformer
Viaarxiv icon