General-purpose language models that can solve various language-domain t...
Software and System logs record runtime information about processes exec...
The cost of vision-and-language pre-training has become increasingly
pro...
We introduce BotSIM, a modular, open-source Bot SIMulation environment w...
Automated software debugging is a crucial task for improving the product...
Deep learning has been actively applied to time-series forecasting, lead...
Existing continual learning methods use Batch Normalization (BN) to
faci...
Deep learning has been actively studied for time series forecasting, and...
Transformers have been actively studied for time-series forecasting in r...
Vision-Language Pre-training (VLP) has advanced the performance for many...
According to Complementary Learning Systems (CLS)
theory <cit.> in neuro...
We introduce Merlion, an open-source machine learning library for time
s...
Large-scale vision and language representation learning has shown promis...
For an image query, unsupervised contrastive learning labels crops of th...
Detection and recognition of scene texts of arbitrary shapes remain a gr...
The ResNet and its variants have achieved remarkable successes in variou...
One crucial challenge of real-world multilingual speech recognition is t...
Semi-supervised learning has been an effective paradigm for leveraging
u...
Existing dialogue state tracking (DST) models require plenty of labeled ...
It is not clear yet why ADAM-alike adaptive gradient algorithms suffer f...
We consider online change detection of high dimensional data streams wit...
Most existing object instance detection and segmentation models only wor...
Low-light imaging is challenging since images may appear to be dark and
...
The use of pre-trained language models has emerged as a promising direct...
Training deep object detectors requires significant amount of human-anno...
Remarkable progress has been made in object instance detection and
segme...
The accuracy of deep learning (e.g., convolutional neural networks) for ...
Learning effective fusion of multi-modality features is at the heart of
...
In this paper, we propose a novel Question-Guided Hybrid Convolution (QG...
The linearly constrained nonconvex nonsmooth program has drawn much atte...
Conventional learning with expert advice methods assumes a learner is al...