Res2Net: A New Multi-scale Backbone Architecture
BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge
Adversarial NLI: A New Benchmark for Natural Language Understanding
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
Mixed Precision Training
Massively Multilingual Neural Machine Translation
Adversarial Representation Learning for Robust Privacy Preservation in\n Audio
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Gaussian Error Linear Units (GELUs)
TextBoxes++: A Single-Shot Oriented Scene Text Detector
Denoising Diffusion Implicit Models
Deep learning for cardiac image segmentation: A review
Robust Optimization for Multilingual Translation with Imbalanced Data
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Making Pre-trained Language Models Better Few-shot Learners
Deep Directed Generative Autoencoders
Distilling the Knowledge in a Neural Network
Neural Natural Language Inference Models Enhanced with External Knowledge
Ecological Consequences of Trophic Cascades: A Global Perspective
Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
