Architectures

Online Multiple Object Tracking With Cross-Task Synergy CVPR 2021 Online Speaker Diarization Equipped with Discriminative Modeling and Guided Inference Interspeech 2021 Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers Interspeech 2021 On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory AAAI 2021 On Monotonic Linear Interpolation of Neural Network Parameters ICML 2021 On Orthogonality Constraints for Transformers ACL 2021 On Position Embeddings in BERT ICLR 2021 On Provable Benefits of Depth in Training Graph Convolutional Networks NeurIPS 2021 On Pursuit of Designing Multi-modal Transformer for Video Grounding EMNLP 2021 On random kernels of residual architectures UAI 2021 On Robustness and Transferability of Convolutional Neural Networks CVPR 2021 On Scalar Embedding of Relative Positions in Attention Models AAAI 2021 On Self-Distilling Graph Neural Network IJCAI 2021 On Smoother Attributions using Neural Stochastic Differential Equations IJCAI 2021 On the application of Transformers for estimating the difficulty of Multiple-Choice Questions from text EACL 2021 On the Approximation Power of Two-Layer Networks of Random ReLUs COLT 2021 On the Bottleneck of Graph Neural Networks and its Practical Implications ICLR 2021 On the cross-lingual transferability of multilingual prototypical models across NLU tasks ACL 2021 On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis ICLR 2021 On the Design of Deep Priors for Unsupervised Audio Restoration Interspeech 2021 On the Effects of Transformer Size on In- and Out-of-Domain Calibration EMNLP 2021 On the Embeddings of Variables in Recurrent Neural Networks for Source Code NAACL 2021 On the Equivalence between Neural Network and Support Vector Machine NeurIPS 2021 On the Frequency Bias of Generative Models NeurIPS 2021 On the Generalization of Learning-Based 3D Reconstruction WACV 2021