Architectures

Outlier Dimensions that Disrupt Transformers are Driven by Frequency EMNLP 2022 Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models NeurIPS 2022 Out of Distribution Data Detection Using Dropout Bayesian Neural Networks AAAI 2022 Overcoming a Theoretical Limitation of Self-Attention ACL 2022 Overlapped Frequency-Distributed Network: Frequency-Aware Voice Spoofing Countermeasure Interspeech 2022 Overparameterization of Deep ResNet: Zero Loss and Mean-field Analysis JMLR 2022 OW-DETR: Open-World Detection Transformer CVPR 2022 P3Depth: Monocular Depth Estimation With a Piecewise Planarity Prior CVPR 2022 P3LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training EMNLP 2022 PACE: Predictive and Contrastive Embedding for Unsupervised Action Segmentation IJCAI 2022 PAIGE: Personalized Adaptive Interactions Graph Encoder for Query Rewriting in Dialogue Systems EMNLP 2022 Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction EMNLP 2022 Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention AAAI 2022 PANDAS@Abusive Comment Detection in Tamil Code-Mixed Data Using Custom Embeddings with LaBSE ACL 2022 PanopticDepth: A Unified Framework for Depth-Aware Panoptic Segmentation CVPR 2022 Panoptic SegFormer: Delving Deeper Into Panoptic Segmentation With Transformers CVPR 2022 PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining NAACL 2022 Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition Interspeech 2022 Paragraph-based Transformer Pre-training for Multi-Sentence Inference NAACL 2022 Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences ICLR 2022 Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition Interspeech 2022 Parameter-Efficient Masking Networks NeurIPS 2022 Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models COLING 2022 Parameter-free Dynamic Graph Embedding for Link Prediction NeurIPS 2022 Parametric Visual Program Induction with Function Modularization ICML 2022