Neural Machine Translation (NMT) models have become successful, but thei...
Generative large language models (LLMs) have shown great success in vari...
The growth and diversity of machine learning applications motivate a
ret...
Stochastic approximation with multiple coupled sequences (MSA) has found...
Open domain entity state tracking aims to predict reasonable state chang...
Deep learning has been widely used for protein engineering. However, it ...
Nowadays, machine learning is one of the most common technology to turn ...
Standard federated optimization methods successfully apply to stochastic...
Due to the incompleteness of knowledge graphs (KGs), zero-shot link
pred...
Building query graphs from natural language questions is an important st...
In continual learning (CL), the goal is to design models that can learn ...
Deep learning often requires a large amount of data. In real-world
appli...
Imbalanced datasets are commonplace in modern machine learning problems....
Neural Architecture Search (NAS) is a popular method for automatically
d...
Active learning is the set of techniques for intelligently labeling larg...
Model pruning is an essential procedure for building compact and
computa...
Short text is becoming more and more popular on the web, such as Chat
Me...
Princeton WordNet (PWN) is a lexicon-semantic network based on cognitive...
Modern neural network architectures often generalize well despite contai...
Modern neural networks are typically trained in an over-parameterized re...