| On polymorphic gradual typing Y Igarashi, T Sekiyama, A Igarashi Proceedings of the ACM on Programming Languages 1 (ICFP), 1-29, 2017 | 72* | 2017 |
| Weighted automata extraction from recurrent neural networks via regression on state spaces T Okudono, M Waga, T Sekiyama, I Hasuo Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5306-5314, 2020 | 60 | 2020 |
| Profile-guided memory optimization for deep neural networks T Sekiyama, T Imamichi, H Imai, R Raymond arXiv preprint arXiv:1804.10001, 2018 | 29* | 2018 |
| Dynamic type inference for gradual Hindley–Milner typing Y Miyazaki, T Sekiyama, A Igarashi Proceedings of the ACM on Programming Languages 3 (POPL), 1-29, 2019 | 27 | 2019 |
| Polymorphic manifest contracts, revised and resolved T Sekiyama, A Igarashi, M Greenberg ACM Transactions on Programming Languages and Systems 39 (1), 3:1--3:36, 2017 | 23* | 2017 |
| Bidirectional learning for time-series models with hidden units T Osogami, H Kajino, T Sekiyama International Conference on Machine Learning, 2711-2720, 2017 | 21 | 2017 |
| Manifest contracts for datatypes T Sekiyama, Y Nishida, A Igarashi Proceedings of the 42th ACM SIGPLAN Symposium on Principles of Programming …, 2015 | 21 | 2015 |
| Temporal Verification with Answer-Effect Modification: Dependent Temporal Type-and-Effect System with Delimited Continuations T Sekiyama, H Unno Proceedings of the ACM on Programming Languages 7 (POPL), 2079-2110, 2023 | 19 | 2023 |
| Multi-stage Neural Networks with Single-sided Classifiers for False Positive Reduction and its Evaluation using Lung X-ray CT Images M Sakamoto, H Nakano, K Zhao, T Sekiyama arXiv preprint arXiv:1703.00311, 2017 | 18 | 2017 |
| Real-time resource usage reduction in artificial neural networks T Sekiyama, K Kawachiya, TD Le, Y Negishi US Patent 10,268,951, 2019 | 17 | 2019 |
| Weighted cascading convolutional neural networks T Sekiyama, M Sakamoto, H Nakano, K Zhao US Patent 10,599,978, 2020 | 15 | 2020 |
| Towards neural-network-guided program synthesis and verification N Kobayashi, T Sekiyama, I Sato, H Unno Formal Methods in System Design, 1-33, 2025 | 12 | 2025 |
| Large Model Support for Deep Learning in Caffe and Chainer M Cho, T Le, U Finkler, H Imai, Y Negishi, T Sekiyama, S Vinod, V Zolotov, ... SysML, 2018 | 12 | 2018 |
| Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic T Sekiyama, A Imanishi, K Suenaga arXiv preprint arXiv:1706.06462, 2017 | 12 | 2017 |
| Stateful manifest contracts T Sekiyama, A Igarashi Proceedings of the 44th ACM SIGPLAN Symposium on Principles of Programming …, 2017 | 12 | 2017 |
| Answer Refinement Modification: Refinement Type System for Algebraic Effects and Handlers F Kawamata, H Unno, T Sekiyama, T Terauchi Proceedings of the ACM on Programming Languages 8 (POPL), 115-147, 2024 | 11 | 2024 |
| Automated proof synthesis for propositional logic with deep neural networks T Sekiyama, K Suenaga arXiv preprint arXiv:1805.11799, 2018 | 10 | 2018 |
| Lung nodule classification by the combination of fusion classifier and cascaded convolutional neural networks M Sakamoto, H Nakano, K Zhao, T Sekiyama 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018 …, 2018 | 10 | 2018 |
| Involving CPUs into Multi-GPU Deep Learning TD Le, T Sekiyama, Y Negishi, H Imai, K Kawachiya Proceedings of the 2018 ACM/SPEC International Conference on Performance …, 2018 | 10 | 2018 |
| Handling polymorphic algebraic effects T Sekiyama, A Igarashi European Symposium on Programming, 353-380, 2019 | 9 | 2019 |
Atsushi IgarashiProfessor, Graduate School of Informatics, Kyoto UniversityVerified email at kuis.kyoto-u.ac.jp
