Res2Net: A New Multi-scale Backbone Architecture
Mixed Precision Training
Adversarial NLI: A New Benchmark for Natural Language Understanding
CE-Net: Context Encoder Network for 2D Medical Image Segmentation
Massively Multilingual Neural Machine Translation
BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge
Adversarial Representation Learning for Robust Privacy Preservation in\n Audio
Gaussian Error Linear Units (GELUs)
Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
Robust Optimization for Multilingual Translation with Imbalanced Data
Neural Natural Language Inference Models Enhanced with External Knowledge
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Deep Directed Generative Autoencoders
Denoising Diffusion Implicit Models
Ecological Consequences of Trophic Cascades: A Global Perspective
Whitening Sentence Representations for Better Semantics and Faster Retrieval
