LLMs usually exhibit limitations in their ability to incorporate new
kno...
Clinical trials are vital in advancing drug development and evidence-bas...
Clinical trials are critical for drug development but often suffer from
...
Drug development is a complex process that aims to test the efficacy and...
Despite many efforts to address the disparities, the underrepresentation...
Large language models (LLMs) specializing in natural language generation...
The mission of open knowledge graph (KG) completion is to draw new findi...
Clinical predictive models often rely on patients electronic health reco...
Foundation models are pre-trained on massive data to perform well across...
Clinical trials are critical for drug development. Constructing the
appr...
Clinical trials are essential to drug development but time-consuming, co...
Synthetic electronic health records (EHRs) that are both realistic and
p...
Many real-world multi-label prediction problems involve set-valued
predi...
The vast amount of health data has been continuously collected for each
...
Structure-based drug design (SBDD) aims to discover drug candidates by
f...
Existing vision-text contrastive learning like CLIP aims to match the pa...
Drug recommendation assists doctors in prescribing personalized medicati...
A clinical trial is an essential step in drug development, which is ofte...
The COVID-19 pandemic has caused devastating economic and social disrupt...
Clinical trials are essential for drug development but are extremely
exp...
Molecular optimization is a fundamental goal in the chemical sciences an...
Cross-sectional prediction is common in many domains such as healthcare,...
We develop Temporal Quantile Adjustment (TQA), a general method to const...
Tabular data (or tables) are the most widely used data format in machine...
Low-rank tensor factorization or completion is well-studied and applied ...
The ongoing pandemic has highlighted the importance of reliable and effi...
Molecule design is a fundamental problem in molecular science and has
cr...
Many fundamental problems affecting the care of critically ill patients ...
Given a deep learning model trained on data from a source site, how to d...
Deep neural network (DNN) classifiers are often overconfident, producing...
Tensor completion aims at imputing missing entries from a partially obse...
Objective: In this paper, we aim to learn robust vector representations ...
In medicine, survival analysis studies the time duration to events of
in...
Information bottleneck (IB) depicts a trade-off between the accuracy and...
The structural design of functional molecules, also called molecular
opt...
Tensor decompositions are powerful tools for dimensionality reduction an...
Existing tensor completion formulation mostly relies on partial observat...
Crucial for building trust in deep learning models for critical real-wor...
Real-world spatio-temporal data is often incomplete or inaccurate due to...
Deep learning is revolutionizing predictive healthcare, including
recomm...
Medication recommendation is an essential task of AI for healthcare. Exi...
Thanks to the increasing availability of genomics and other biomedical d...
Despite deep learning (DL) success in classification problems, DL classi...
Clinical trials are crucial for drug development but are time consuming,...
Researchers require timely access to real-world longitudinal electronic
...
Accurate prediction of the transmission of epidemic diseases such as COV...
To test the possibility of differentiating chest x-ray images of COVID-1...
Counterfactual prediction is about predicting outcome of the unobserved
...
Successful health risk prediction demands accuracy and reliability of th...
Existing tensor factorization methods assume that the input tensor follo...