No 1. 《A literature survey of matrix methods for data science》
No 2. 《Optimization for deep learning: theory and algorithms》
No 3. 《Are Transformers universal approximators of sequence-to-sequence functions?》
No 4. 《Generating Positive Bounding Boxes for Balanced Training of Object Detectors》
No 5. 《PointRend: Image Segmentation as Rendering》
No 6. 《Deep Audio Prior》
No 7. 《Adversarial Representation Active Learning》
No 8. 《Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation》
No 9. 《ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language》
No 10. 《Measuring Dataset Granularity》
No 11. 《Mastering Complex Control in MOBA Games with Deep Reinforcement Learning》
No 12. 《Σ-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction》
No 13. 《DeepSFM: Structure From Motion Via Deep Bundle Adjustment》
No 14. 《Early Detection of Research Trends》
No 15. 《Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax》
No 16. 《Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining》
No 17. 《Continuous Meta-Learning without Tasks》
No 18. 《Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve》
No 19. 《secml: A Python Library for Secure and Explainable Machine Learning》
No 20. 《AutoScale: Learning to Scale for Crowd Counting》
No 21. 《Learning a Spatio-Temporal Embedding for Video Instance Segmentation》
No 22. 《UMAP does not preserve global structure any better than t-SNE when using the same initialization》
No 23. 《Audio-Visual Embodied Navigation》
No 24. 《Topic subject creation using unsupervised learning for topic modeling》
No 25. 《Molecular Generative Model Based On Adversarially Regularized Autoencoder》
No 26. 《Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision》
No 27. 《Learning Singing From Speech》
No 28. 《RPGAN: GANs Interpretability via Random Routing》
No 29. 《CNN-generated images are surprisingly easy to spot… for now》
No 30. 《Joint Face Super-Resolution and Deblurring Using a Generative Adversarial Network》