22 citations · 46 across the 9 of their papers we have counts for
5 papers · 1 filter
An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning
Shaohuai Shi, Qing Yang, Yang Xiang +2
To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for…
Improve Ranking Correlation of Super-net through Training Scheme from One-shot NAS to Few-shot NAS
Jiawei Liu, Kaiyu Zhang, Weitai Hu +1
The algorithms of one-shot neural architecture search(NAS) have been widely used to reduce computation consumption. However, because of the interference among the subnets in which…
An Empirical Study on Disentanglement of Negative-free Contrastive Learning
Jinkun Cao, Ruiqian Nai, Qing Yang +2
Negative-free contrastive learning methods have attracted a lot of attention with simplicity and impressive performances for large-scale pretraining. However, its disentanglement p…
Orbital hybridization and electrostatic interaction in a double molecule transistor
Xiao Guo, Qing Yang, Wei Yu +5
Understanding the intermolecular interactions and utilize these interactions to effectively control the transport behavior of single molecule is the key step from single molecule d…
Thermodynamically consistent master equation based on subsystem eigenstates
Si-Ying Wang, Qinghong Yang, Fu-Lin Zhang
Master equations under appropriate assumptions are efficient tools for the study of open quantum systems. For many-body systems, subsystems of which locally couple to thermal baths…