Trieu H. Trinh
Google Brain Resident
Biomedical data and benchmarks are highly valuable yet very limited in
l...
We present ViT5, a pretrained Transformer-based encoder-decoder model fo...
We introduce a pretraining technique called Selfie, which stands for
SEL...
Commonsense reasoning is a long-standing challenge for deep learning. Fo...
Despite recent advances in training recurrent neural networks (RNNs),
ca...