Architectures

The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks COLT 2022 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NeurIPS 2022 The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization ICLR 2022 The Neural Race Reduction: Dynamics of Abstraction in Gated Networks ICML 2022 Theoretical analysis of deep neural networks for temporally dependent observations NeurIPS 2022 Theoretically Provable Spiking Neural Networks NeurIPS 2022 The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study ACL 2022 "The Pedestrian Next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping CVPR 2022 The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy CVPR 2022 The Psychology of Semantic Spaces: Experiments with Positive Emotion (Student Abstract) AAAI 2022 The role of optimization geometry in single neuron learning AISTATS 2022 The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks ICLR 2022 The RoyalFlush System for the WMT 2022 Efficiency Task EMNLP 2022 The Sample Complexity of One-Hidden-Layer Neural Networks NeurIPS 2022 The Separation Capacity of Random Neural Networks JMLR 2022 The SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes NAACL 2022 The trade-offs of model size in large recommendation models : 100GB to 10MB Criteo-tb DLRM model NeurIPS 2022 The Uncanny Similarity of Recurrence and Depth ICLR 2022 The Untapped Potential of Off-the-Shelf Convolutional Neural Networks WACV 2022 The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022 ACL 2022 The VolcTrans System for WMT22 Multilingual Machine Translation Task EMNLP 2022 THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption ACL 2022 The YiTrans Speech Translation System for IWSLT 2022 Offline Shared Task ACL 2022 Three Real-World Datasets and Neural Computational Models for Classification Tasks in Patent Landscaping EMNLP 2022 TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes SemEval 2022