We propose a text-to-image generation algorithm based on deep neural net...
Despite recent advances in implicit neural representations (INRs), it re...
Although autoregressive models have achieved promising results on image
...
For autoregressive (AR) modeling of high-resolution images, vector
quant...
DETR is the first end-to-end object detector using a transformer
encoder...
Large-batch training has been essential in leveraging large-scale datase...
Unsupervised representation learning has recently received lots of inter...
While tasks could come with varying number of instances in realistic
set...
We propose a Bayesian optimization method over sets, to minimize a black...
A meta-model is trained on a distribution of similar tasks such that it
...
The order of the tasks a continual learning model encounters may have la...
We present a personalized and reliable prediction model for healthcare, ...
While variational dropout approaches have been shown to be effective for...
Few-shot learning aims to build a learner that quickly generalizes to no...
Attention mechanism is effective in both focusing the deep learning mode...
Hyperparameter optimization undergoes extensive evaluations of validatio...
Locality-sensitive hashing (LSH) is a popular data-independent indexing
...