Transformers

One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks EMNLP 2022 One Wug, Two Wug+s Transformer Inflection Models Hallucinate Affixes ACL 2022 On Improving Adversarial Transferability of Vision Transformers ICLR 2022 Online Decision Transformer ICML 2022 On Target Representation in Continuous-output Neural Machine Translation ACL 2022 On the Connection between Local Attention and Dynamic Depth-wise Convolution ICLR 2022 On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning NeurIPS 2022 On the Integration of Self-Attention and Convolution CVPR 2022 On the Interpretability of Attention Networks ACML 2022 On the Locality of Attention in Direct Speech Translation ACL 2022 On the Prediction Network Architecture in RNN-T for ASR Interspeech 2022 On the Representation Collapse of Sparse Mixture of Experts NeurIPS 2022 On the Role of Bidirectionality in Language Model Pre-Training EMNLP 2022 On the Use of Bert for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation NAACL 2022 Open Vocabulary Electroencephalography-to-Text Decoding and Zero-Shot Sentiment Classification AAAI 2022 Open Vocabulary Extreme Classification Using Generative Models ACL 2022 Optimal-er Auctions through Attention NeurIPS 2022 Optimize_Prime@DravidianLangTech-ACL2022: Abusive Comment Detection in Tamil ACL 2022 Optimize_Prime@DravidianLangTech-ACL2022: Emotion Analysis in Tamil ACL 2022 Optimizing Relevance Maps of Vision Transformers Improves Robustness NeurIPS 2022 Orca: A Distributed Serving System for Transformer-Based Generative Models OSDI 2022 Orthogonal Transformer: An Efficient Vision Transformer Backbone with Token Orthogonalization NeurIPS 2022 OSSEM: one-shot speaker adaptive speech enhancement using meta learning Interspeech 2022 Outlier Dimensions that Disrupt Transformers are Driven by Frequency EMNLP 2022 Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models NeurIPS 2022