Architectures

The expressive power of pooling in Graph Neural Networks NeurIPS 2023 The Helsinki-NLP Submissions at NADI 2023 Shared Task: Walking the Baseline EMNLP 2023 The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023 The HW-TSC’s Simultaneous Speech-to-Text Translation System for IWSLT 2023 Evaluation ACL 2023 The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks COLT 2023 The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks ICLR 2023 The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023 The Importance of Anti-Aliasing in Tiny Object Detection ACML 2023 The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks ICLR 2023 The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers ICLR 2023 The Lie Derivative for Measuring Learned Equivariance ICLR 2023 The Locality and Symmetry of Positional Encodings EMNLP 2023 The MAKE-NMTVIZ System Description for the WMT23 Literary Task EMNLP 2023 The Making and Breaking of Camouflage ICCV 2023 The MALACH Corpus: Results with End-to-End Architectures and Pretraining Interspeech 2023 The MineTrans Systems for IWSLT 2023 Offline Speech Translation and Speech-to-Speech Translation Tasks ACL 2023 The Naughtyformer: A Transformer Understands and Moderates Adult Humor (Student Abstract) AAAI 2023 The NLP Task Effectiveness of Long-Range Transformers EACL 2023 The Numerical Stability of Hyperbolic Representation Learning ICML 2023 Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks NeurIPS 2023 Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks EACL 2023 The Power of Recursion in Graph Neural Networks for Counting Substructures AISTATS 2023 The Role of Global and Local Context in Named Entity Recognition ACL 2023 The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit NeurIPS 2023 The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation NeurIPS 2023