No 1. 《Graph Structured Network for Image-Text Matching》
    No 2. 【博士论文：自然语言深度潜变量模型】
    No 3. 《Multi-Head Attention: Collaborate Instead of Concatenate》
    No 4. 《PyTorch Distributed: Experiences on Accelerating Data Parallel Training》
    No 5. 《APQ: Joint Search for Nerwork Architecture, Pruning and Quantization Policy》
    No 6. 《Model-based Reinforcement Learning: A Survey》
    No 7. 《Fair k-Means Clustering》
    No 8. 《Discovering Symbolic Models from Deep Learning with Inductive Biases》
    No 9. 《Knowledge-Aware Language Model Pretraining》
    No 10. 《Differentiable Top-k Operator with Optimal Transport》
    No 11. 《HRank: Filter Pruning using High-Rank Feature Map》
    No 12. 《GhostNet: More Features from Cheap Operations》
    No 13. 《SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness》
    No 14. 《Statistical Mechanics of Generalization in Kernel Regression》
    No 15. 《An EM Approach to Non-autoregressive Conditional Sequence Generation》
    No 16. 《One Thousand and One Hours: Self-driving Motion Prediction Dataset》
    No 17. 《Time-varying Graph Representation Learning via Higher-Order Skip-Gram with Negative Sampling》
    No 18. 《Graph Optimal Transport for Cross-Domain Alignment》
    No 19. 《Machine learning-based clinical prediction modeling — A practical guide for clinicians》
    No 20. 《Matern Gaussian processes on Riemannian manifolds》
    No 21. 《Topological Insights in Sparse Neural Networks》
    No 22. 《Stochastic Differential Equations with Variational Wishart Diffusions》
    No 23. 《Pre-training via Paraphrasing》
    No 24. 《MUMBO: MUlti-task Max-value Bayesian Optimization》
    No 25. 《Fair Hierarchical Clustering》
    No 26. 《Swapping Autoencoder for Deep Image Manipulation》
    No 27. 《Making DensePose fast and light》
    No 28. 《Subgraph Neural Networks》
    No 29. 《I know why you like this movie: Interpretable Efficient Multimodal Recommender》
    No 30. 《Sparse GPU Kernels for Deep Learning》