The field of protein folding research has been greatly advanced by deep
...
Soft robots have demonstrated superior flexibility and functionality tha...
Deep learning-based approaches, such as AlphaFold2 (AF2), have significa...
RNA structure determination and prediction can promote RNA-targeted drug...
Most of today's AI systems focus on using self-attention mechanisms and
...
Commonsense reasoning (CSR) requires the model to be equipped with gener...
Recent advances in large-scale pre-training such as GPT-3 allow seemingl...
Multimodal pre-training has propelled great advancement in
vision-and-la...
In this paper, we propose Cross-Thought, a novel approach to pre-trainin...
Existing language model compression methods mostly use a simple L2 loss ...
Transformer has become ubiquitous in the deep learning field. One of the...
Existing approaches to real-time question answering (RTQA) rely on learn...
Large-scale cross-lingual language models (LM), such as mBERT, Unicoder ...
Protein contacts provide key information for the understanding of protei...
In this paper, we present Hierarchical Graph Network (HGN) for multi-hop...
We present a large, tunable neural conversational response generation mo...
Adversarial training, which minimizes the maximal risk for label-preserv...
Pre-trained language models such as BERT have proven to be highly effect...
Recently exciting progress has been made on protein contact prediction, ...
Structured high-cardinality data arises in many domains, and poses a maj...
Deep Convolutional Neural Networks (DCNN) has shown excellent performanc...
We present a framework for incorporating prior information into nonparam...
Learning the network structure underlying data is an important problem i...