Deep Learning

Noise-Robust Learning from Multiple Unsupervised Sources of Inferred Labels AAAI 2022 Non-Autoregressive Chinese ASR Error Correction with Phonological Training NAACL 2022 Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework NAACL 2022 Non-autoregressive Translation with Layer-Wise Prediction and Deep Supervision AAAI 2022 Non-neural Models Matter: a Re-evaluation of Neural Referring Expression Generation Systems ACL 2022 Noun-MWP: Math Word Problems Meet Noun Answers COLING 2022 On Scrambling Phenomena for Randomly Initialized Recurrent Networks NeurIPS 2022 On the difficulty of learning chaotic dynamics with RNNs NeurIPS 2022 On the Implicit Bias of Gradient Descent for Temporal Extrapolation AISTATS 2022 Optimally Controllable Perceptual Lossy Compression ICML 2022 Outlier Dimensions that Disrupt Transformers are Driven by Frequency EMNLP 2022 ParaDetox: Detoxification with Parallel Data ACL 2022 Perceptual Quality Assessment of Omnidirectional Images AAAI 2022 Personalized Federated Learning through Local Memorization ICML 2022 Personalized Public Policy Analysis in Social Sciences Using Causal-Graphical Normalizing Flows AAAI 2022 PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures CVPR 2022 Pyramid Architecture for Multi-Scale Processing in Point Cloud Segmentation CVPR 2022 Quality-Aware Decoding for Neural Machine Translation NAACL 2022 R(Det)2: Randomized Decision Routing for Object Detection CVPR 2022 Regex in a Time of Deep Learning: The Role of an Old Technology in Age Discrimination Detection in Job Advertisements ACL 2022 Reverse-mode differentiation in arbitrary tensor network format: with application to supervised learning JMLR 2022 Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction IJCAI 2022 Robust Training under Label Noise by Over-parameterization ICML 2022 SALTED: A Framework for SAlient Long-tail Translation Error Detection EMNLP 2022 Score Matched Neural Exponential Families for Likelihood-Free Inference JMLR 2022