A simple framework for contrastive learning of visual representations
This paper presents SimCLR: a simple framework for contrastive learning of visual
representations. We simplify recently proposed contrastive self-supervised learning algorithms …
representations. We simplify recently proposed contrastive self-supervised learning algorithms …
Big self-supervised models are strong semi-supervised learners
One paradigm for learning from few labeled examples while making best use of a large
amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. …
amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. …
[HTML][HTML] Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography
…, L Liang, T Wu, R Deng, K Wei, Y Zhou, T Chen… - Cell, 2020 - cell.com
Many COVID-19 patients infected by SARS-CoV-2 virus develop pneumonia (called novel
coronavirus pneumonia, NCP) and rapidly progress to respiratory failure. However, rapid …
coronavirus pneumonia, NCP) and rapidly progress to respiratory failure. However, rapid …
Cigarette smoking and colorectal cancer incidence and mortality: Systematic review and meta‐analysis
PS Liang, TY Chen… - International journal of …, 2009 - Wiley Online Library
The association between cigarette smoking and colorectal cancer (CRC) has been controversial.
To synthesize the available data, we conducted a comprehensive meta‐analysis of all …
To synthesize the available data, we conducted a comprehensive meta‐analysis of all …
Characterization of spike glycoprotein of SARS-CoV-2 on virus entry and its immune cross-reactivity with SARS-CoV
…, T Chen, J Hu, Z Xiang, Z Mu, X Chen, J Chen… - Nature …, 2020 - nature.com
Since 2002, beta coronaviruses (CoV) have caused three zoonotic outbreaks, SARS-CoV in
2002–2003, MERS-CoV in 2012, and the newly emerged SARS-CoV-2 in late 2019. …
2002–2003, MERS-CoV in 2012, and the newly emerged SARS-CoV-2 in late 2019. …
Graph contrastive learning with augmentations
Generalizable, transferrable, and robust representation learning on graph-structured data
remains a challenge for current graph neural networks (GNNs). Unlike what has been …
remains a challenge for current graph neural networks (GNNs). Unlike what has been …
A survey on the security of blockchain systems
Since its inception, the blockchain technology has shown promising application prospects.
From the initial cryptocurrency to the current smart contract, blockchain has been applied to …
From the initial cryptocurrency to the current smart contract, blockchain has been applied to …
Thermally activated delayed fluorescence materials towards the breakthrough of organoelectronics
Y Tao, K Yuan, T Chen, P Xu, H Li, R Chen… - Advanced …, 2014 - Wiley Online Library
The design and characterization of thermally activated delayed fluorescence (TADF)
materials for optoelectronic applications represents an active area of recent research in …
materials for optoelectronic applications represents an active area of recent research in …
Stabilizing triplet excited states for ultralong organic phosphorescence
The control of the emission properties of synthetic organic molecules through molecular
design has led to the development of high-performance optoelectronic devices with tunable …
design has led to the development of high-performance optoelectronic devices with tunable …
[HTML][HTML] Polygenic risk scores for prediction of breast cancer and breast cancer subtypes
Stratification of women according to their risk of breast cancer based on polygenic risk scores
(PRSs) could improve screening and prevention strategies. Our aim was to develop PRSs, …
(PRSs) could improve screening and prevention strategies. Our aim was to develop PRSs, …