Architectures

On Quantizing Implicit Neural Representations WACV 2023 On Representing Linear Programs by Graph Neural Networks ICLR 2023 On Representing Mixed-Integer Linear Programs by Graph Neural Networks ICLR 2023 On Robustness of Finetuned Transformer-based NLP Models EMNLP 2023 On Search Strategies for Document-Level Neural Machine Translation ACL 2023 On Separate Normalization in Self-supervised Transformers NeurIPS 2023 On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation ICML 2023 On the Ability of Graph Neural Networks to Model Interactions Between Vertices NeurIPS 2023 On the Benefits of Learning to Route in Mixture-of-Experts Models EMNLP 2023 On the complexity of nonsmooth automatic differentiation ICLR 2023 On the Compositional Generalization in Versatile Open-domain Dialogue ACL 2023 On The Computational Complexity of Self-Attention ALT 2023 On the Convergence of Encoder-only Shallow Transformers NeurIPS 2023 On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters ICML 2023 On the Difference of BERT-style and CLIP-style Text Encoders ACL 2023 On the Dynamics Under the Unhinged Loss and Beyond JMLR 2023 On the Expressive Flexibility of Self-Attention Matrices AAAI 2023 On the Expressive Power of Geometric Graph Neural Networks ICML 2023 On the Expressivity Role of LayerNorm in Transformers’ Attention ACL 2023 On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition Interspeech 2023 On the Forward Invariance of Neural ODEs ICML 2023 On the impact of activation and normalization in obtaining isometric embeddings at initialization NeurIPS 2023 On the Impact of Cross-Domain Data on German Language Models EMNLP 2023 On the Initialization of Graph Neural Networks ICML 2023 On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks AISTATS 2023