| Discovering the compositional structure of vector representations with role learning networks P Soulos, T McCoy, T Linzen, P Smolensky arXiv preprint arXiv:1910.09113, 2019 | 47 | 2019 |
| Enriching transformers with structured tensor-product representations for abstractive summarization Y Jiang, A Celikyilmaz, P Smolensky, P Soulos, S Rao, H Palangi, ... arXiv preprint arXiv:2106.01317, 2021 | 19 | 2021 |
| Learning hierarchical visual representations in deep neural networks using hierarchical linguistic labels JC Peterson, P Soulos, A Nematzadeh, TL Griffiths arXiv preprint arXiv:1805.07647, 2018 | 18 | 2018 |
| Context-aware system for providing fitness information P Soulos, A Gale US Patent App. 14/812,379, 2017 | 10 | 2017 |
| Differentiable tree operations promote compositional generalization P Soulos, EJ Hu, K McCurdy, Y Chen, R Fernandez, P Smolensky, J Gao International Conference on Machine Learning, 32499-32520, 2023 | 8 | 2023 |
| Disentangled deep generative models reveal coding principles of the human face processing network P Soulos, L Isik PLOS Computational Biology 20 (2), e1011887, 2024 | 4* | 2024 |
| Structural biases for improving transformers on translation into morphologically rich languages P Soulos, S Rao, C Smith, E Rosen, A Celikyilmaz, RT McCoy, Y Jiang, ... arXiv preprint arXiv:2208.06061, 2022 | 3 | 2022 |
| Compositional Generalization Across Distributional Shifts with Sparse Tree Operations P Soulos, H Conklin, M Opper, P Smolensky, J Gao, R Fernandez The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024 | 1 | 2024 |
| Recurrent Transformers Trade-off Parallelism for Length Generalization on Regular Languages P Soulos, A Terzic, M Hersche, A Rahimi The First Workshop on System-2 Reasoning at Scale, NeurIPS'24, 2024 | | 2024 |
| Toward Compositional Behavior in Neural Models: A Survey of Current Views K McCurdy, P Soulos, P Smolensky, R Fernandez, J Gao Proceedings of the 2024 Conference on Empirical Methods in Natural Language …, 2024 | | 2024 |
Paul SmolenskyMicrosoft Research Redmond & Krieger-Eisenhower Professor of Cognitive Science, Johns Hopkins在 jhu.edu 的电子邮件经过验证
