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