No 1. 《Dynamic Convolution: Attention over Convolution Kernels》
No 2. 【用大规模深度强化学习挑战Dota 2:OpenAI Five 如何打败世界冠军(Team OG)】
No 3. 《Recurrent Neural Networks (RNNs): A gentle Introduction and Overview》
No 4. 《AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty》
No 5. 《Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey》
No 6. 《Deep Learning for Visual Tracking: A Comprehensive Survey》
No 7. 《Why ADAM Beats SGD for Attention Models》
No 8. 《Meta-Learning without Memorization》
No 9. 《Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis》
No 10. 《The Group Loss for Deep Metric Learning》
No 11. 《Multimodal Self-Supervised Learning for Medical Image Analysis》
No 12. 《Manifold Markov chain Monte Carlo methods for Bayesian inference in a wide class of diffusion models》
No 13. 《Self-Supervised 3D Keypoint Learning for Ego-motion Estimation》
No 14. 《Encoding Musical Style with Transformer Autoencoders》
No 15. 《Full-Gradient Representation for Neural Network Visualization》
No 16. 《Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection》
No 17. 《15 Keypoints Is All You Need》
No 18. 《Lower Bounds for Non-Convex Stochastic Optimization》
No 19. 《Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One》
No 20. 《Digital Twin: Acquiring High-Fidelity 3D Avatar from a Single Image》
No 21. 《Noise2Blur: Online Noise Extraction and Denoising》
No 22. 《Deep Ensembles: A Loss Landscape Perspective》
No 23. 《Reinforcement Learning Upside Down: Don’t Predict Rewards — Just Map Them to Actions》
No 24. 《Learning to Predict Explainable Plots for Neural Story Generation》
No 25. 《Face Beautification: Beyond Makeup Transfer》
No 26. 《Geometric Capsule Autoencoders for 3D Point Clouds》
No 27. 《Putting An End to End-to-End: Gradient-Isolated Learning of Representations》
No 28. 《12-in-1: Multi-Task Vision and Language Representation Learning》
No 29. 《Advances and Open Problems in Federated Learning》
No 30. 《Learning a Neural 3D Texture Space from 2D Exemplars》