Paul SoulosI am a PhD candidate in Computational Cognitive Science at Johns Hopkins University and a collaborating researcher with the Microsoft Research Deep Learning Group. My research focuses on advancing artificial intelligence’s capacity for human-like generalization through innovative approaches in algorithmic reasoning and neural network design. Key research contributions:
Before entering graduate school, I worked as a software engineer at Google and Fitbit. My focus at these companies was on wearables and health technology. CV / GitHub / Google Scholar |
|
Selected Publications
|
Compositional Generalization Across Distributional Shifts with Sparse Tree OperationsPaul Soulos, Henry Conklin, Mattia Opper, Paul Smolensky, Jianfeng Gao, Roland Fernandez Thirty-seventh Conference on Neural Information Processing Systems, 2024 Spotlight Award Spotlight oral presentation at System 2 Reasoning Workshop, NeurIPS 2024 paper / poster / |
|
Recurrent Transformers Trade-off Parallelism for Length Generalization on Regular LanguagesPaul Soulos, Aleksandar Terzić, Michael Hersche, Abbas Rahimi The First Workshop on System-2 Reasoning at Scale, NeurIPS'24, 2024 paper / |
|
Toward Compositional Behavior in Neural Models: A Survey of Current ViewsKate McCurdy, Paul Soulos, Paul Smolensky Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024 paper / |
|
Disentangled Face Representations in Humans and MachinesPaul Soulos, Leyla Isik PLOS Computational Biology, 2024 arxiv / paper / code / poster / |
|
Differentiable Tree Operations Promote Compositional GeneralizationPaul Soulos, Edward Hu, Kate McCurdy, Yunmo Chen, Roland Fernandez, Paul Smolensky, Jianfeng Gao Proceedings of the 40th International Conference on Machine Learning, 2023 arxiv / paper / code / poster / |
|
Structural Biases for Improving Transformers on Translation into Morphologically Rich LanguagesPaul Soulos, Sudha Rao, Caitlin Smith, Eric Rosen, Asli Celikyilmaz, R. Thomas McCoy, Yichen Jiang, Coleman Haley, Roland Fernandez, Hamid Palangi, Jianfeng Gao, Paul Smolensky Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021), 2021 arxiv / |
|
Enriching Transformers with Structured Tensor-Product Representations for Abstractive SummarizationYichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021 arxiv / |
|
Discovering the Compositional Structure of Vector Representations with Role Learning NetworksPaul Soulos, R. Thomas McCoy, Tal Linzen, Paul Smolensky Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2020 Spotlight oral presentation at Workshop on Context and Compositionality in Biological and Artificial Neural Systems, NeurIPS 2019 arxiv / code / |
|
Learning to generalize like humans using basic-level object labelsJoshua C Peterson, Paul Soulos, Aida Nematzadeh, Thomas L Griffiths Journal of Vision, 2019 arxiv / |
|
Design and source code from Jon Barron's website |