| Autoformalization with large language models Y Wu, AQ Jiang, W Li, M Rabe, C Staats, M Jamnik, C Szegedy Advances in neural information processing systems 35, 32353-32368, 2022 | 311 | 2022 |
| Draft, sketch, and prove: Guiding formal theorem provers with informal proofs AQ Jiang, S Welleck, JP Zhou, W Li, J Liu, M Jamnik, T Lacroix, Y Wu, ... arXiv preprint arXiv:2210.12283, 2022 | 280 | 2022 |
| Concept embedding models: Beyond the accuracy-explainability trade-off M Espinosa Zarlenga, P Barbiero, G Ciravegna, G Marra, F Giannini, ... Advances in neural information processing systems 35, 21400-21413, 2022 | 274 | 2022 |
| Variational autoencoders for cancer data integration: design principles and computational practice N Simidjievski, C Bodnar, I Tariq, P Scherer, H Andres Terre, Z Shams, ... Frontiers in genetics 10, 1205, 2019 | 165 | 2019 |
| Thor: Wielding hammers to integrate language models and automated theorem provers AQ Jiang, W Li, S Tworkowski, K Czechowski, T Odrzygóźdź, P Miłoś, ... Advances in Neural Information Processing Systems 35, 8360-8373, 2022 | 152 | 2022 |
| You shouldn’t trust me: Learning models which conceal unfairness from multiple explanation methods. B Dimanov, U Bhatt, M Jamnik, A Weller IOS Press, 2020 | 146 | 2020 |
| Do concept bottleneck models learn as intended? A Margeloiu, M Ashman, U Bhatt, Y Chen, M Jamnik, A Weller arXiv preprint arXiv:2105.04289, 2021 | 125 | 2021 |
| Evaluating language models for mathematics through interactions KM Collins, AQ Jiang, S Frieder, L Wong, M Zilka, U Bhatt, T Lukasiewicz, ... Proceedings of the National Academy of Sciences 121 (24), e2318124121, 2024 | 120 | 2024 |
| Mathematical reasoning with diagrams M Jamnik University of Chicago Press, 2001 | 105 | 2001 |
| Now you see me (cme): concept-based model extraction D Kazhdan, B Dimanov, M Jamnik, P Liò, A Weller arXiv preprint arXiv:2010.13233, 2020 | 99 | 2020 |
| Abstract diagrammatic reasoning with multiplex graph networks D Wang, M Jamnik, P Lio arXiv preprint arXiv:2006.11197, 2020 | 76 | 2020 |
| On automating diagrammatic proofs of arithmetic arguments M Jamnik, A Bundy, I Green Journal of logic, language and information 8 (3), 297-321, 1999 | 68 | 1999 |
| What makes an effective representation of information: a formal account of observational advantages G Stapleton, M Jamnik, A Shimojima Journal of Logic, Language and Information 26 (2), 143-177, 2017 | 59 | 2017 |
| Human uncertainty in concept-based ai systems KM Collins, M Barker, M Espinosa Zarlenga, N Raman, U Bhatt, M Jamnik, ... Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 869-889, 2023 | 58 | 2023 |
| Interpretable neural-symbolic concept reasoning P Barbiero, G Ciravegna, F Giannini, ME Zarlenga, LC Magister, A Tonda, ... International Conference on Machine Learning, 1801-1825, 2023 | 54 | 2023 |
| What is a proof? A Bundy, M Jamnik, A Fugard Philosophical Transactions of the Royal Society A: Mathematical, Physical …, 2005 | 54 | 2005 |
| Efficient decompositional rule extraction for deep neural networks ME Zarlenga, Z Shams, M Jamnik arXiv preprint arXiv:2111.12628, 2021 | 45 | 2021 |
| Multilingual mathematical autoformalization AQ Jiang, W Li, M Jamnik arXiv preprint arXiv:2311.03755, 2023 | 43 | 2023 |
| Learned low precision graph neural networks Y Zhao, D Wang, D Bates, R Mullins, M Jamnik, P Lio arXiv preprint arXiv:2009.09232, 2020 | 43 | 2020 |
| Lucie Charlotte Magister, Alberto Tonda, Pietro Lio, Frederic Precioso, Mateja Jamnik, and Giuseppe Marra. Interpretable neural-symbolic concept reasoning P Barbiero, G Ciravegna, F Giannini, ME Zarlenga International Conference on Machine Learning, 1801-1825, 2023 | 42 | 2023 |
Pietro LiòProfessor, University of CambridgeVerified email at cam.ac.uk
