Open-domain conversation systems integrate multiple conversation skills ...
While generative modeling on multimodal image-text data has been activel...
Episodic count has been widely used to design a simple yet effective
int...
Natural language modeling with limited training data is a challenging
pr...
In this report, we summarize the takeaways from the first NeurIPS 2021
N...
Consistency regularization on label predictions becomes a fundamental
te...
Large-batch training has been essential in leveraging large-scale datase...
Unsupervised representation learning has recently received lots of inter...
Self-supervised learning has been widely used to obtain transferrable
re...
Data augmentation has been actively studied for robust neural networks. ...
A split-transform-merge strategy has been broadly used as an architectur...
NeurIPS 2019 AutoDL challenge is a series of six automated machine learn...
We design and implement a ready-to-use library in PyTorch for performing...
Most convolutional neural networks (CNNs) for image classification use a...
Conditional generative adversarial networks (cGANs) have gained a
consid...
In this paper, a neural architecture search (NAS) framework is proposed ...
In this paper, we propose a novel edge-labeling graph neural network (EG...
Data augmentation is an indispensable technique to improve generalizatio...
Learning to infer Bayesian posterior from a few-shot dataset is an impor...