No 1. 《Stanza: A Python Natural Language Processing Toolkit for Many Human Languages》
No 2. 《Pre-trained Models for Natural Language Processing: A Survey》
No 3. 《Hyper-Parameter Optimization: A Review of Algorithms and Applications》
No 4. 《Rethinking Batch Normalization in Transformers》
No 5. 《Convolutional Kernel Networks for Graph-Structured Data》
No 6. 《A New Meta-Baseline for Few-Shot Learning》
No 7. 《AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data》
No 8. 《What Information Does a ResNet Compress?》
No 9. 《Extended Batch Normalization》
No 10. 《TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding》
No 11. 《Sampling on Graphs: From Theory to Applications》
No 12. 《Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking》
No 13. 《OpenGAN: Open Set Generative Adversarial Networks》
No 14. 《Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images》
No 15. 《The twitter explorer: a framework for observing Twitter through interactive networks》
No 16. 《Ford Multi-AV Seasonal Dataset》
No 17. 《KGvec2go — Knowledge Graph Embeddings as a Service》
No 18. 《Tracking COVID-19 using online search》
No 19. 《Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective》
No 20. 《Semantic Pyramid for Image Generation》
No 21. 《Synthesizing human-like sketches from natural images using a conditional convolutional decoder》
No 22. 《Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks》
No 23. 《A Survey of End-to-End Driving: Architectures and Training Methods》
No 24. 《Self-supervised Single-view 3D Reconstruction via Semantic Consistency》
No 25. 《Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems》
No 26. 《Equalization Loss for Long-Tailed Object Recognition》
No 27. 《On the Convergence of Adam and Adagrad》
No 28. 《SDVTracker: Real-Time Multi-Sensor Association and Tracking for Self-Driving Vehicles》
No 29. 《Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling》
No 30. 《Blur, Noise, and Compression Robust Generative Adversarial Networks》