BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge
Massively Multilingual Neural Machine Translation
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
Mixed Precision Training
Res2Net: A New Multi-scale Backbone Architecture
CE-Net: Context Encoder Network for 2D Medical Image Segmentation
Adversarial Representation Learning for Robust Privacy Preservation in\n Audio
Deep Directed Generative Autoencoders
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Distilling the Knowledge in a Neural Network
Visual Relationship Detection with Language Priors
Whitening Sentence Representations for Better Semantics and Faster Retrieval
Gaussian Error Linear Units (GELUs)
Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
Neural Natural Language Inference Models Enhanced with External Knowledge
TextBoxes++: A Single-Shot Oriented Scene Text Detector
Ecological Consequences of Trophic Cascades: A Global Perspective
Robust Optimization for Multilingual Translation with Imbalanced Data
