Generative pre-trained Transformer (GPT) has demonstrates its great succ...
Filler words like “um" or “uh" are common in spontaneous speech. It is
d...
Transformer-based autoregressive (AR) methods have achieved appealing
pe...
Protein language models have excelled in a variety of tasks, ranging fro...
Recent research has revealed that neural language models at scale suffer...
Molecular representation learning has attracted much attention recently....
Drug-Target Affinity (DTA) prediction is an essential task for drug disc...
Non-autoregressive (NAR) generation, which is first proposed in neural
m...
The lack of labeled data is a major obstacle to learning high-quality
se...
Molecular conformation generation aims to generate three-dimensional
coo...
Sequential recommendation methods play an important role in real-world
r...
Understanding protein sequences is vital and urgent for biology, healthc...
The Interaction between Drugs and Targets (DTI) in human body plays a cr...
Dropout is a powerful and widely used technique to regularize the traini...
Learning dynamics governed by differential equations is crucial for
pred...
Transformer architecture achieves great success in abundant natural lang...
With sequentially stacked self-attention, (optional) encoder-decoder
att...
Stock trend forecasting has become a popular research direction that att...
Improving sample efficiency is a key research problem in reinforcement
l...
Simultaneous neural machine translation (briefly, NMT) has attracted muc...
Machine teaching uses a meta/teacher model to guide the training of a st...
While the multi-branch architecture is one of the key ingredients to the...
The recently proposed BERT has shown great power on a variety of natural...
We Microsoft Research Asia made submissions to 11 language directions in...
The encoder-decoder based neural machine translation usually generates a...
While very deep neural networks have shown effectiveness for computer vi...
While data augmentation is an important trick to boost the accuracy of d...
Teaching is critical to human society: it is with teaching that prospect...
Neural machine translation usually adopts autoregressive models and suff...
Recent studies have shown that reinforcement learning (RL) is an effecti...
Machine translation has made rapid advances in recent years. Millions of...
In this paper, we study a new learning paradigm for Neural Machine
Trans...