Researcher in Artificial Intelligence
Last updated: March 2025. Always out of date...
In the meantime, some of the publications (typically not medical or educational research) can be found here.
IntCEMs. (ICML 2025)
Mateo
NMA-tune. (ICML 2025)
Julia
Multimodal lego: Model merging and fine-tuning across topologies and modalities in biomedicine. (ICLR 2025)
Hemker, K., Simidjievski, N. and Jamnik, M.
In the Thirteenth International Conference on Learning Representations, ICLR 2025.
Measuring cross-modal interactions in multimodal models. (AAAI 2025)
Wenderoth, L., Hemker, K., Simidjievski, N. and Jamnik, M.
In The 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025.
Neural reasoning for sure through constructing explainable models. (AAAI 2025)
Dong, T., Jamnik, M. and Lio, P.
In The 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025.
Future themes in regulating artificial intelligence in investment management.
Buczynski, W., Steffek, F., Jamnik, M., Cuzzolin, F. and Sahakian, B.
Computer Law and Security Review, 56:106111. Elsevier. 2025.
RO-FIGS: Efficient and expressive tree-based ensembles for tabular data.
Matjasec, U., Simidjievski, N. and Jamnik, M.
In IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx), pages IEEECITREx2025-25. IEEE. 2025.
Multi-language diversity benefits autoformalization. (NeurIPS 2024)
Jiang, A.Q., Li, W. and Jamnik, M.
In Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems, NeurIPS 2024.
HEALNet: Multimodal fusion for heterogeneous biomedical data. (NeurIPS 2024)
Hemker, K., Simidjievski, N. and Jamnik, M.
In Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems, NeurIPS 2024.
TabEBM: A tabular data augmentation method with class-specific energy-based models. (NeurIPS 2024)
Margeloiu, A., Jian, X., Simidjievski, N. and Jamnik, M.
In Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems, NeurIPS 2024.
Repurposing language models into embedding models: Finding the compute-optimal recipe. (NeurIPS 2024)
Jiang, A.Q., Ziarko, A., Piotrowski, B., Li, W., Jamnik, M. and Milos, P.
In Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems, NeurIPS 2024.
End-to-end ontology learning with large language models. (NeurIPS 2024)
Lo, A., Jiang, A.Q., Li, W. and Jamnik, M.
In Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems, NeurIPS 2024.
GCondNet: A novel method for improving neural networks on small high-dimensional tabular data. (TMLR 2024)
Margeloiu, A.i, Simidjievski, N., Lio, P. and Jamnik, M.
Transactions on Machine Learning Research.
Efficient bias mitigation without privileged information. (ECCV 2024)
Espinosa Zarlenga, M., Sankaranarayanan, S., Andrews, J., Shams, Z., Jamnik, M. and Xiang, A.
In Leonardis, A. et al (eds.), European Conference in Computer Vision, ECCV 2024, Lecture Notes in Computer Science. Springer.
Top 5% paper, oral.
ProtoGate: Prototype-based neural networks with global-to-local feature selection for tabular biomedical data. (ICML 2024)
Jiang, X., Margeloiu, A., Simidjievski, N. and Jamnik, M.
In International Conference on Machine Learning, ICML 2024, PMLR, 235:21844-21878.
Understanding inter-concept relationships in concept-based models. (ICML 2024)
Raman, N., Espinosa Zarlenga, M. and Jamnik, M.
In International Conference on Machine Learning, ICML 2024, PMLR, 235:42009-42025.
Evaluating language models for mathematics through interactions. (PNAS 2024)
Collins, K.M., Jiang, A.Q., Frieder, S., Wong, L., Zilka, M., Bhatt, U., Lukasiewicz, T., Wu, Y., Tenenbaum, J.B., Hart, W., Gowers, T., Li, W., Weller, A. and Jamnik, M.
Proc. National Academy of Sciences of the USA, 121(24): e2318124121. (PNAS).
Oruga: Implementation and use of representational systems theory.
Raggi, D., Stapleton, G., Stockdill, A., Garcia Garcia, G., Cheng, P.C.H. and Jamnik, M.
In Kohlhase, A. and Kovacs, L., (eds.), Intelligent Computer Mathematics (CICM), volume 14960 of LNCS, pages 345--351. Springer. 2024.
Index systems: Enumerating their forms and explaining their diversity with representational interpretive structure theory. (CogSci 2024)
Cheng, P.C.H., Garcia Garcia, G., Raggi, D. and Jamnik, M.
In 45th Annual Conference of the Cognitive Science Society (CogSci 2024). Cognitive Science Society.
Decoding expertise: Exploring cognitive micro-behavioural measurements for visualization competence. (CogSci 2024)
Colarusso, F., Cheng, P.C.H., Grau, D., Garcia~Garcia, G., Raggi, D. and Jamnik, M.
In 45th Annual Conference of the Cognitive Science Society (CogSci 2024). Cognitive Science Society.
A human information processing theory of the interpretation of visualizations: Demonstrating its utility. (CHI 2024)
Cheng, P.C.H., Garcia~Garcia, G., Raggi, D. and Jamnik, M.
In CHI 2024: CHI Conference on Human Factors in Computing Systems, 194:1--194:14. ACM.
Dynamics-Informed Protein Design with Structure Conditioning. (ICLR 2024).
Komorowska, U.J., Mathis, S.V., Didi, K., Vargas, F., Lio, P. and Jamnik, M.
In The Twelfth International Conference on Learning Representations, ICLR 2024. OpenReview.net.
Generation of visual representations for multi-modal mathematical knowledge. (AAAI 2024).
Wu, L., Choi, S., Raggi, D., Stockdill, A., Garcia Garcia, G., Colarusso, F., Cheng, P.C.-H. and Jamnik, M.
In Wooldridge, M. et al, (eds.), Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, pages 23850--23852. AAAI Press.
Representational Systems Theory: A Unified Approach to Encoding, Analysing and Transforming Representations.
Raggi, D., Stapleton, G., Jamnik, M., Stockdill, A., Garcia Garcia, G. and Cheng, P.C.H. (2024)
CSLI Press, Stanford, Forthcoming. Available at arXiv:2206.03172.
Learning to receive help: Intervention-aware concept embedding models. (NeurIPS 2023).
Espinosa Zarlenga, M., Collins, K., Dvijotham, K., Weller, A., Shams, Z. and Jamnik, M.
In Oh, Alice at al (eds.), Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing
Systems 2023, NeurIPS 2023.
TabCBM: Concept-based interpretable neural networks for tabular data. (TMLR July 2023).
Espinosa Zarlenga, M., Shams, Z., Nelson, M.E., Kim, B. and Jamnik, M.
Transactions on Machine Learning Research.
Human visual consistency-checking in the real world ontologies. (VLHCC 2023).
Sato, Y., Stapleton, G., Jamnik, M., Shams, Z. and Blake, A.
In IEEE Symposium on Visual Languages and Human-Centric Computing, VL/HCC 2023, pages 249--251. IEEE.
Interpretable Neural-Symbolic Concept Reasoning. (ICML 2023).
Barbiero, P., Ciravegna, G., Giannini, F., Espinosa Zarlenga, M., Magister, L.C., Tonda, A., Lio, P.,
Precioso, F., Jamnik, M. and Marra, G.
In Krause, A. et al (eds.), International Conference on Machine Learning, (ICML 2023), volume 202 of Proceedings of Machine Learning Research, pages 1801-1825. PMLR.
Draft, sketch, and prove: Guiding formal theorem provers with informal proofs. (ICLR 2023).
Jiang, Albert Q., Welleck, S., Zhou, J.P., Lacroix, T., Liu, J., Li, W., Jamnik, M., Lample, G. and Wu, Y.
In International Conference on Learning Representations (ICLR). OpenReview.net.
Top 5% paper, oral.
A novel interaction for competence assessment using micro-behaviors: Extending CACHET to graphs and charts. (CHI 2023).
Colarusso, F., Cheng, P.C.H., Garcia Garcia, G., Stockdill, A., Raggi, D. and Jamnik, M.
In Mueller, S., Williamson, J. and Wilson, M.L., CHI: Conference on Human Factors in Computing Systems. ACM.
Towards robust metrics for concept representation evaluation. (AAAI 2023).
Espinosa Zarlenga, M., Shams, Z., Barbiero, P., Kazhdan, D., Bhatt, U., Weller, A. and Jamnik, M.
In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023. AAAI Press.
Oral.
Weight predictor network with feature selection for small sample tabular biomedical data. (AAAI 2023).
Margeloiu, A., Simidjievski, N., Lio, P. and Jamnik, M.
In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023. AAAI Press.
Human Uncertainty in Concept-Based AI Systems. (AIES 2023).
Collins, K.M., Barker, M., Espinosa Zarlenga, M., Raman, N., Bhatt, U., Jamnik, M., Sucholutsky, I., Weller, A. and Dvijotham, K.
In AIES '23: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, pages 869--889. ACM.AAAI/ACS AIES.
CGXplain: Rule-based deep neural network explanations using dual linear programs. (TML4H 2023).
Hemker, K., Shams, Z. and Jamnik, M.
In Chen, H. and Luo, L. (eds.), Trustworthy Machine Learning for Healthcare WS, (TML4H), volume 13932 of Lecture Notes in Computer Science, pages 60-72. Springer.
Concept Distillation in Graph Neural Networks. (xAI 2023).
Magister, L.C., Barbiero, P., Kazhdan, D., Siciliano, F., Ciravegna, G., Silvestri, F., Jamnik, M. and Lio, P.
In Longo, L., (ed.), Explainable Artificial Intelligence, xAI 2023, volume 1903 of Communications in Computer and Information Science, pages 233--255. Springer.
Discrete lagrangian neural networks with automatic symmetry discovery. (2023).
Lishkova, Y., Scherer, P., Ridderbusch, S., Jamnik, M., Lio, P., Ober-Bloebaum, S. and Offen, C.
IFAC-PapersOnLine, 56(2):3203--3210. 22nd IFAC World Congress.
Concept embedding models: Beyond the Accuracy-Explainability Trade-Off. (NeurIPS 2022).
Espinosa~Zarlenga, M., Barbiero, P., Ciravegna, G., Marra, G., Giannini, F., Diligenti, M., Shams, Z., Precioso, F., Melacci, S., Weller, A., Lio, P. and Jamnik, M.
In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022.
Thor: Wielding hammers to integrate language models and automated theorem provers. (NeurIPS 2022).
Jiang, A.Q., Li, W., Tworkowski, S., Czechowski, K., Odrzygozdz, T., Milos, P., Wu, Y. and Jamnik, M.
In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022.
Autoformalization with large language models. (NeurIPS 2022).
Wu, Y., Jiang, A.Q., Li, W., Rabe, M.N., Staats, C., Jamnik, M. and Szegedy, C.
In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022.
Distributed representations of graphs for drug pair scoring. (LOG 2022).
Scherer, P., Lio, P. and Jamnik, M.
In Proceedings of the First Learning on Graphs Conference, volume 198(22):1-17. PMLR.
Representational interpretive structure: Theory and notation. (Diagrams 2022).
Cheng, P.C.-H., Stockdill, A., Garcia Garcia, G., Raggi, D. and Jamnik, M.
In Giardino, V., Linker, S., Burns, R., Bellucci, F., Boucheix, J-M and Viana, P., (eds.), Diagrammatic Representation and Inference - 13th International Conference, Diagrams 2022, volume 13462 of Lecture Notes
in Computer Science, pages 54-69. Springer.
Evaluating colour in concept diagrams. (Diagrams 2022).
McGrath, S., Blake, A., Stapleton, G., Touloumis, A., Chapman, P., Jamnik, M. and Shams, Z.
In Giardino, V., Linker, S., Burns, R., Bellucci, F., Boucheix, J-M and Viana, P., (eds.), Diagrammatic Representation and Inference - 13th International Conference, Diagrams 2022, volume 13462 of Lecture Notes
in Computer Science, pages 168-184. Springer.
Examining experts’ recommendations of representational systems for problem solving. (VLHCC 2022).
Stockdill, A., Stapleton, G., Raggi, D., Jamnik, M., Garcia Garcia, G. and Cheng, P.C.-H.
In 2022 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC), pages 1--6. IEEE.
Unsupervised construction of computational graphs for gene expression data with explicit structural inductive biases.
Scherer, P., Trebacz, M., Simidjievski, N., Vinas, R., Shams, Z., Andres-Terre, H., Jamnik, M. and Lio, P. (2022).
Bioinformatics, 38(5):1320-1327.
Two primary school teachers’ mathematical knowledge of content, students, and teaching practices relevant to lakatos-style investigation of proof tasks. (CERME 2022).
Deslis, D., Stylianides, A.J. and Jamnik, M.
In Twelfth Congress of the European Society for Research in Mathematics Education (CERME12), volume hal-03746873v2. HAL Open Science.
Chinese teachers’ professional noticing of students’ reasoning in the context of Lakatos-style proving activity. (CERME 2022).
Yang, M., Stylianides, A.J. and Jamnik, M.
In Twelfth Congress of the European Society for Research in Mathematics Education (CERME12), volume hal-03748414v2. HAL Open Science.
Oruga: an avatar of representational systems theory. (HLC 2022).
Raggi, D., Stapleton, G., Jamnik, M., Stockdill, A., Garcia~Garcia, G. and Cheng, P.C.-H.
In Bundy, A. and Mareschal, D., (eds.), Proceedings of the 3rd Human-Like Computing Workshop (HLC 2022) co-located with the 2nd International Joint Conference on Learning and Reasoning (IJCLR} 2022), volume 3227 of CEUR Workshop Proceedings, pages 1-5. CEUR-WS.org.
Cognitive analysis for representation change. (HLC 2022).
Stockdill, A., Garcia~Garcia, G., Cheng, P.C.-H., Raggi, D. and Jamnik, M.
In Bundy, A. and Mareschal, D., (eds.), Proceedings of the 3rd Human-Like Computing Workshop (HLC 2022) co-located with the 2nd International Joint Conference on Learning and Reasoning (IJCLR 2022), volume 3227 of CEUR Workshop Proceedings, pages 6-10. CEUR-WS.org.
On the relation between distributionally robust optimization and data curation. (AAAI 2022).
Slowik, A., Bottou, L., Holden, S.B. and Jamnik, M.
In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, pages 13053--13054. AAAI Press.
Logical reasoning with diagrams.
Jamnik, M. (2021).
In Knauff, M. and Spohn, W., (eds.), Handbook of Rationality, chapter 13, pages 715-723. MIT Press.
Endowing machines with the expert human ability to select
representations: why and how.
Jamnik, M. and Cheng, P.C.H. (2021).
In Muggleton, S. and Chater, N., (eds.), Human-Like Machine Intelligence, chapter 18, pages 355-378. Oxford University Press.
Human-like computational reasoning: Diagrams and other representations.
Jamnik, M. (2021).
In Michaelson, G., (ed.), Mathematical Reasoning: The History
and Impact of the DReaM Group, chapter 7, pages 129-145. Springer.
Primary school teachers’ mathematical knowledge for Lakatos-style proof instruction.
Deslis, D., Stylianides, A.J. and Jamnik, M. (PME 2021).
In Inprasitha, M., Changsri, N. and Boonsena, N., (eds.),
Proceedings of the 44th Conference of the International Group for the
Psychology of Mathematics Education (PME44), volume 2, pages 185-192.
Considerations in representation selection for problem solving: A review.
Stockdill, A., Raggi, D., Jamnik, M., Garcia~Garcia, G. and Cheng, P.C.H. (Diagrams 2021).
In Basu, A., Stapleton, G., Linker, S., Legg, C., Manalo, E. and
Viana, P., (eds.), Diagrammatic Representation and Inference - 12th
International Conference, Diagrams 2021, volume 12909 of LNCS, pages 35-51. Springer.
Best Student Paper Award.
Cognitive properties of representations: A framework.
Cheng, P.C.H., Garcia~Garcia, G., Raggi, D., Stockdill, A. and Jamnik, M. (Diagrams 2021).
In Basu, A., Stapleton, G., Linker, S., Legg, C., Manalo, E. and
Viana, P., (eds.), Diagrammatic Representation and Inference - 12th
International Conference, Diagrams 2021, volume 12909 of LNCS, pages
415-430. Springer.
Observing strategies of drawing data representations.
Colarusso, F., Cheng, P.C.H., Garcia Garcia, G., Raggi, D. and Jamnik, M. (Diagrams 2021).
In Basu, A., Stapleton, G., Linker, S., Legg, C., Manalo, E. and
Viana, P., (eds.), Diagrammatic Representation and Inference - 12th
International Conference, Diagrams 2021, volume 12909 of LNCS, pages
537-552. Springer.
A graphical user interface framework for formal verification.
Ayers, E.W., Jamnik, M. and Gowers, W.T. (ITP 2021).
In Cohen, L. and Kaliszyk, C., (eds.), 12th International
Conference on Interactive Theorem Proving, ITP, volume 193 of
LIPIcs, pages 4:1-4:16. Schloss Dagstuhl - Leibniz-Zentrum fur
Informatik.
Is disentanglement all you need? comparing concept-based and disentanglement approaches.
Kazhdan, D., Dimanov, B., Andres-Terre, H., Jamnik, M., Lio, P. and Weller, A. (2021).
In ICLR workshop Responsible AI, volume abs/2104.06917. CoRR.
Do concept bottleneck models learn as intended?
Margeloiu, A., Ashman, M., Bhatt, U., Chen, Y., Jamnik, M. and Weller, A. (2021).
In ICLR workshop Responsible AI, volume abs/2105.04289. CoRR.
Efficient decompositional rule extraction for deep neural networks.
Espinosa Zarlenga, M., Shams, Z. and Jamnik, M. (2021).
In NeurIPS workshop XAI4Debugging, volume abs/2111.12628. CoRR.
Failing conceptually: Concept-based explanations of dataset shift.
Wijaya, M.A., Kazhdan, D., Dimanov, B. and Jamnik, M. (2021).
In ICLR workshop Responsible AI, volume abs/2104.08952. CoRR.
Pairwise relations discriminator for unsupervised raven's progressive matrices.
Quek Wei Kiat, N., Wang, D. and Jamnik, M. (2021).
In ICLR workshop MATHAI, volume abs/2011.01306. CoRR.
How to (Re)represent it?
Raggi, D., Stapleton, G., Stockdill, A., Jamnik, M., Garcia~Garcia, G. and Cheng, P.C.H. (ICTAI 2020).
In 32th IEEE International Conference on Tools with Artificial Intelligence, pages 1224-1232. IEEE.
You shouldn’t trust me: Learning models which conceal unfairness from multiple explanation methods.
Dimanov, B., Bhatt, U., Jamnik, M. and Weller, A. (ECAI 2020).
In De Giacomo, G., Catala, A., Dilkina, B., Milano, M., Barro, S.,
Bugarín, A. and Lang, J., (eds.), European Conference on Artificial
Intelligence (ECAI): Frontier in Artificial Intelligence and Applications,
volume 325, pages 2473-2480. IOS Press.
Abstract diagrammatic reasoning with multiplex graph networks.
Wang, D., Jamnik, M. and Lio, P. (ICLR 2020).
In International Conference on Learning Representations (ICLR). OpenReview.net.
Bayesian optimisation for premise selection in automated theorem proving.
Slowik, A., Mangla, C., Jamnik, M., Holden, S.B. and Paulson, L.C. (AAAI 2020).
In AAAI Conference on Artificial Intelligence, volume 34 of Student abstract, pages 13919-13920. AAAI Press.
Dissecting representations.
Raggi, D., Stockdill, A., Jamnik, M., Garcia Garcia, G., Sutherland, H.E.A. and Cheng, P.C.H. (Diagrams 2020).
In Pietarinen, A.V., Chapman, P., Bosveld-de Smet, L., Giardino, V.,
Corter, J. and Linker, S., (eds.), Diagrams: Diagrammatic
Representation and Inference, volume 12169 of LNCS, pages 144-152.
Springer.
Correspondence-based analogies for choosing problem representations.
Stockdill, A., Raggi, D., Jamnik, M., Garcia Garcia, G., Sutherland, H.E.A., Cheng, P.C.H. and Sarkar, A. (VLHCC 2020).
In Anslow, C., Hermans, F. and Tanimoto, S., (eds.), IEEE Symposium on Visual Languages and Human-Centric Computing, VL/HCC 2020, pages 1-5. IEEE.
Cross-domain correspondences for explainable recommendations.
Stockdill, A., Raggi, D., Jamnik, M., Garcia Garcia, G., Sutherland, H.E.A., Cheng, P.C.H and Sarkar, A. (2020).
In Smith-Renner, et al (eds.), Proceedings of the Workshop on Explainable Smart Systems for Algorithmic Transparency in Emerging Technologies co-located with 25th International Conference on Intelligent User Interfaces (IUI 2020), volume 2582 of CEUR Workshop Proceedings. CEUR-WS.org.
Now you see me (CME): Concept-based model extraction.
Kazhdan, D., Dimanov, B., Jamnik, M., Lio, P. and Weller, A. (2020).
In Conrad, S. and Tiddi, I., (eds.), CIKM ’20: 29th ACM International Conference on Information and Knowledge Management, AIMLAI WS, volume 2699 of CEUR Workshop Proceedings. CEUR-WS.org.
MEME: generating RNN model explanations via model extraction.
Kazhdan, D., Dimanov, B., Jamnik, M. and Lio, P. (2020).
In NeurIPS workshop HAMLETS, volume abs/2012.06954. CoRR.
Improving interpretability in medical imaging diagnosis using adversarial training.
Margeloiu, A., Simidjievski, N., Jamnik, M. and Weller, A. (2020).
In NeurIPS WS Medical Imaging meet NeurIPS, volume abs/2012.01166. CoRR.
Incorporating network based protein complex discovery into automated model construction.
Scherer, P., Trebacz, M., Simidjievski, N., Shams, Z., Andres-Terre, H., Lio, P. and Jamnik, M. (2020).
In 15th Machine Learning in Computational Biology (MLCB20), volume abs/2010.00387. CoRR.
Using ontology embeddings for structural inductive bias in gene expression data analysis.
Trebacz, M., Shams, Z., Jamnik, M., Scherer, P., Simidjievski, N., Andres-Terre, H. and Lio, P. (2020).
In 15th Machine Learning in Computational Biology (MLCB20), volume abs/2011.10998. CoRR.
Probabilistic dual network architecture search on graphs.
Zhao, Y., Wang, D., Gao, X., Mullins, R.D., Lio, P. and Jamnik, M. (2020).
In AAAI workshop DLG, volume abs/2003.09676. CoRR.
Learned low precision graph neural networks.
Zhao, Y., Wang, D., Bates, D., Mullins, R.D., Jamnik, M. and Lio, P. (2020).
In EuroSys workshop EuroMLSys, volume abs/2009.09232. CoRR.
Variational autoencoders for cancer data integration: Design
principles and computational practice.
Simidjievski, N., Bodnar, C., Tariq, I., Scherer, P., Andres Terre, H., Shams,
Z., Jamnik, M. and Lio, P. (2019).
Frontiers in Genetics, 10:1205 (14pp).
A
common type of rigorous proof that resists Hilbert’s
programme.
Bundy, A. and Jamnik, M. (2019).
In Hanna, G., Reid, D. and de~Villiers, M., (eds.), Proof
Technology in Mathematics Research and Teaching, Mathematics education in
the digital era, chapter 3, pages 59-71. Springer.
Inspection and selection of representations.
Raggi, D., Stockdill, A., Jamnik, M., Garcia~Garcia, G., Sutherland, H.E.A.
and Cheng, P.C.H. (CICM 2019).
In Kaliszyk, C., Brady, E., Kohlhase, A. and Sacerdoti-Coen, C.,
(eds.), Intelligent Computer Mathematics (CICM), volume 11617 of LNCS, pages 227-242. Springer.
A human-oriented term rewriting system.
Ayers, W.E., Gowers, W.T. and Jamnik, M. (KI 2019).
In Benzmueller, C. and Stuckenschmidt, H., (eds.), KI 2019: Advances in Artificial Intelligence, volume 11793 of LNCS, pages 76-86. Springer.
Exploring and Conceptualising Attestation.
Oliver, I., Howse, J., Stapleton, G., Shams, Z., Jamnik, M. (ICCS 2019).
In Endres, D., Alam, M. and Sotropa, D., (eds.), Graph-Based
Representation and Reasoning (ICCS), volume 11530 of LNCS, pages 131-145. Springer.
Human inference beyond syllogisms: an
approach using external graphical representations.
Sato, Y., Stapleton, G., Jamnik, M. and Shams, Z. (2019).
Cognitive Processing, 20(1):103-115.
Unsupervised extraction of interpretable graph representations from multiple-object scenes.
Wang, D., Jamnik, M. and Lio', P. (ICML WS 2019).
In ICML workshop on Learning and Reasoning with
Graph-structured Representation, 11pp.
Unsupervised and interpretable scene discovery with Discrete-Attend-Infer-Repeat.
Wang, D., Jamnik, M. and Lio', P. (ICML WS 2019).
In ICML workshop on Self-Supervised Learning, 9pp.
Step-wise Sensitivity Analysis: Identifying Partially Distributed Representations for Interpretable Deep Learning.
Dimanov, B., Jamnik, M. (ICLR WS 2019).
In ICLR workshop on Debugging Machine Learning Models, 11pp.
Bayesian Optimisation with Gaussian Processes for Premise Selection.
Slowik, A., and Mangla, C. and Jamnik, M. and Holden, S.B. and Paulson, L.C. (SAT WS 2019)
In Kovacz, L and Voronkov, A., (eds.), The 6th Vampire Workshop
at The 22nd International Conference on Theory and Applications of
Satisfiability Testing (SAT 2019), Epic Series in Computing. EasyChair.
iCon: A diagrammatic theorem prover for ontologies.
Shams, Z., Jamnik, M., Stapleton, G. and Sato, Y. (KR 2018).
In Wolter, F., Thielscher, M. and Toni, F., (eds.),
Principles of Knowledge Representation and Reasoning:
Proceedings of the 16th International Conference,
KR 2018. AAAI Press.
Accessible reasoning with diagrams: from cognition to automation.
Shams, Z., Sato, Y., Jamnik, M. and Stapleton, G. (Diagrams 2018).
In P., Chapman, G., Stapleton, A., Moktefi, S., Perez-Kriz
and F., Bellucci, (eds.), Diagrams 2018, volume 10871 of
LNCS, pages 247--263. Springer.
Investigating diagrammatic reasoning with deep neural networks.
Wang, D., Jamnik, M. and Lio', P. (Diagrams 2018).
In P., Chapman, G., Stapleton, A., Moktefi, S., Perez-Kriz
and F., Bellucci, (eds.), Diagrams 2018, volume 10871 of
LNCS, pages 390-398. Springer.
The
observational advantages of Euler diagrams with
existential import.
Stapleton, G., Shimojima, A. and Jamnik, M. (Diagrams 2018).
In P., Chapman, G., Stapleton, A., Moktefi, S.,
Perez-Kriz and F., Bellucci, (eds.), Diagrams 2018, volume
10871 of LNCS, pages 313-329. Springer.
Deductive
reasoning about expressive statements using external
graphical representations.
Sato, Y., Stapleton, G., Jamnik, M. and Shams, Z. (CogSci 2018).
In Rogers, T.T., Rau, M., Zhu, X. and Kalish, C.W,
(eds.), 40th Annual Conference of the Cognitive Science
Society - CogSci, pages 2418-2423. Cognitive Science
Society.
Artificial
intelligence is growing up fast: What’s next for thinking machines?
Cave, S., Jamnik, M. and Hernandez-Orallo, J. (2018).
Research Horizons, 35:26--27. Cambridge University Press.
How network-based and set-based visualizations aid consistency
checking in ontologies.
Sato, Y., Stapleton, G., Jamnik, M., Shams, Z. and Blake, A. (2017).
In Takahashi, S. and Li, J., (eds.), 10th International
Symposium on Visual Information Communication and
Interaction, VINCI-2017, pages 137-141. ACM.
Reasoning with concept diagrams about antipatterns in ontologies.
Shams, Z., Jamnik, M., Stapleton, G. and Sato, Y. (2017)
In Geuvers, H, England, M., Hasan, O., Rabe, F. and Teschke, O.,
(eds.), 10th International Conference on Intelligent Computer
Mathematics - CICM-2017, volume 10383 of Lecture Notes in Computer
Science, pages 255-271. Springer.
Reasoning with concept diagrams about antipatterns.
Shams, Z., Jamnik, M., Stapleton, G. and Sato, Y. (2017)
In Eiter, T., Sands, D., Sutcliffe, G. and Voronkov,
A., (eds.), IWIL@LPAR 2017 Workshop and LPAR-21
Short Presentations, Botswana}, volume 1 of Kalpa
Publications in Computing, pages 27-42. EasyChair.
What
makes an effective representation of information: A
formal account of observational advantages.
Stapleton, G., Jamnik, M. and Shimojima, A. (2017).
Journal of Logic, Language and Information, 26(2):143-177.
Tactical diagrammatic
reasoning.
Linker, S., Burton, J. and Jamnik, M. (2016).
In Autexier, S. and Quaresma, P., (eds.), 12th
International Workshop on User Interfaces for Theorem
Provers, IJCAR, volume 239 of Electronic Proceedings in
Theoretical Computer Science, pages 29-42.
Visual discovery and
model-driven explanation of time series
patterns.
Sarkar, A., Spott, M., Blackwell, A.F. and Jamnik, M.
(2016).
In Blackwell, A., Plimmer, B. and Stapleton, G., (eds.),
IEEE Symposium on Visual Languages and Human-Centric
Computing, VL/HCC 2016, pages 78-86. IEEE.
Highly commended paper (honourable mention).
Diagrammatic
Representation and Inference, 9th International
Conference, Diagrams 2016, Proceedings.
Jamnik, M., Uesaka, Y. and Schwartz, S., (eds.).
(2016).
Volume 9781 of Lecture Notes in
Artificial Intelligence. Springer.
Effective
representation of information: Generalizing free
rides.
Stapleton, G., Jamnik, M. and
Shimojima, A. (2016).
In Jamnik, M., Uesaka, Y. and Schwartz, S., (eds.),
Diagrams, volume 9781 of Lecture Notes in Artificial
Intelligence, pages 296-299. Springer.
Our work in the future.
Jamnik, M. (2016).
Cambridge News, March 7 2016, page 39.
A reasoner for spider diagrams.
Urbas, M., Jamnik, M. and Stapleton, G. (2015).
Journal of Logic, Language and Information.
24(4):487-540.
The end of work?
Jamnik, M. (2015).
BBC Focus Magazine, December Issue 288:56.
Interactive visual machine
learning in spreadsheets.
Sarkar, A., Jamnik,
M., Blackwell, A.F. and Spott, M. (2015b).
In Li, Z., Ermel, C. and Fleming, S.D., (eds.), IEEE
Symposium on Visual Languages and Human-Centric Computing,
VL/HCC 2015, pages 159-163. IEEE.
Interaction
with Uncertainty in Visualisations.
Sarkar, A., Blackwell, A., Jamnik, M. and Spott, M.
(2015a).
Eurographics Conference on Visualization (EuroVis) 2015,
34(3):133-137.
A
framework for heterogeneous reasoning in formal and
informal domains.
Urbas, M. and Jamnik, M. (2014).
In Dwyer, T., Purchase, H.C. and Delaney,
A., (eds.), Diagrams, volume 8578 of Lecture Notes in
Computer Science, pages 277-292. Springer.
Teach
and try: A simple interaction technique for exploratory
data modelling by end users.
Sarkar, A., Blackwell, A.F., Jamnik, M. and Spott, M.
(2014).
In Fleming, S.D., Fish, A. and Scaffidi, C., (eds.), IEEE
Symposium on Visual Languages and Human-Centric Computing,
VL/HCC 2014, pages 53-56. IEEE.
Don's diary.
Jamnik, M. (2014).
CAM Magazine, 73:3. Cambridge University Press.
Designing
Inference Rules for Spider Diagrams.
Stapleton, G., Jamnik, M. and Urbas, M. (2013).
In Kelleher, C., Burnett, M.M. and Sauer, S., (eds.),
IEEE Symposium on Visual Languages and Human-Centric
Computing, VLHCC 2013, pages 19-26.
Diabelli:
A heterogeneous proof system.
Urbas, M. and Jamnik, M. (2012).
In Gramlich, B., Miller, D. and Sattler, U., (eds.),
IJCAR, volume 7364 of Lecture Notes in Artificial
Intelligence, pages 559-566. Springer.
Speedith: A
diagrammatic reasoner for spider diagrams.
Urbas, M., Jamnik, M., Stapleton, G. and Flower, J. (2012).
In Cox, P.T.,
Plimmer, B. and Rodgers, P.J., (eds.), Diagrams,
volume 7352 of Lecture Notes in Artificial
Intelligence, pages 163-177. Springer.
Heterogeneous
Proofs: Spider Diagrams meet Higher-Order
Provers.
Urbas, M. and Jamnik, M. (2011).
In van Eekelen, M., Geuvers, H., Schmaltz, J. and
Wiedijk, F., (eds.), ITP, volume 6898 of Lecture Notes in
Computer Science, pages 376--382. Springer.
Diagrammatic
Representation and Inference, 6th International
Conference, Diagrams 2010, Proceedings.
Goel, A.K., Jamnik, M. and Narayanan, N.H.,
editors. (2010).
Volume 6170 of Lecture Notes in Artificial
Intelligence. Springer.
Heterogeneous reasoning in real
arithmetic.
Urbas, M. and Jamnik, M. (2010).
In A.K. Goel, M. Jamnik, and N.H. Narayanan, editors,
Diagrammatic Representation and Inference, 6th
International Conference, Diagrams 2010, Proceedings,
number 6170 in Lecture Notes in Artificial Intelligence,
pages 345-348. Springer.
Diagrammatic
reasoning in separation logic.
Ridsdale, M., Jamnik, M., Benton, M. and Berdine, J.
(2008).
In Stapleton, G., Howse, J. and Lee, J., (eds.),
Diagrammatic Representation and Inference, 5th
International Conference, Diagrams 2008, Proceedings,
number 5223 in Lecture Notes in Artificial Intelligence,
pages 408-411. Springer.
Combined reasoning by
automated cooperation.
Benzmueller, C., Sorge, V., Jamnik, M. and Kerber,
M. (2008)
Journal of Applied Logic, 6(3):318-342. Elsevier.
Can
machines reason?
Jamnik, M. (2008)
Research Horizons, 5:13. Cambridge University Press.
Kako sklepajo stroji? (How can machines reason?).
Jamnik, M. (2007)
EMZIN - Revija za kulturo, Letnik 17(3-4):88-89.
Lahko stroji sklepajo kot ljudje v matematiki?
(Can machines reason like humans in mathematics?).
Jamnik, M. (2007)
Konferenca slovenskih znanstvenikov in gospodarstvenikov
iz sveta in Slovenije, 5:64-67. Slovenian World
Congress.
On the
comparison of proof planning systems: LambdaClam,
Omega and IsaPlanner.
Dennis, L.A., Jamnik, M. and Pollet, M. (2006)
Electronic Notes in Theoretical Computer Science,
151(1):93-110.
Computer
scientist and a woman?
Jamnik, M. (2005)
Computing. 9 June 2005.
Computer scientist and a woman?
Jamnik, M. (2005)
Newsletter, page 14.
Cambridge University Press, June/July 2005.
What is a proof?
Bundy, A., Jamnik, M. and Fugard, A.
(2005).
Philosophical Transactions of Royal Society A: The Nature of
Mathematical Proof, 363(1835):2377-2391.
Can a
higher-order and a first-order theorem prover
cooperate?
Benzmueller, C., Sorge, V., Jamnik, M. and Kerber, M.
(2005)
In Baader, F. and Voronkov, A., (eds.),
Proceedings of the 11th International Conference on Logic
for Programming and Automated Reasoning, LPAR 2004, number
3452 in Lecture Notes in Artificial Intelligence, pages
415-431. Springer Verlag.
Psychological
validity of schematic proofs.
Jamnik, M. and Bundy, A. (2005)
In Hutter, D. and Stephan, W., (eds.), Mechanizing
Mathematical Reasoning: Essays in Honor of Joerg
H. Siekmann on the Occasion of His 60th Birthday, number
2605 in Lecture Notes in Artificial Intelligence, pages
321-341. Springer Verlag.
An
experimental comparison of diagrammatic and algebraic
logics.
Winterstein, D., Bundy, A., Gurr, C. and Jamnik,
M. (2004)
In Blackwell, A., Marriott, K. and
Shimojima, A., (eds.), Theory and Application of Diagrams:
Third International Conference, Diagrams 2004,
Proceedings, number 2980 in Lecture Notes in Artificial
Intelligence, pages 432-434. Springer Verlag.
On
differences between the real plane and physical plane.
Winterstein, D., Bundy, A. and Jamnik, M. (2004)
In Blackwell, A., Marriott, K. and Shimojima, A., (eds.),
Theory and Application of Diagrams: Third International
Conference, Diagrams 2004, Proceedings, number 2980 in
Lecture Notes in Artificial Intelligence, pages
29-31. Springer Verlag.
Automatic
learning of proof methods in proof planning.
Jamnik, M., Kerber, M., Pollet, M. and Benzmueller,
C. (2003)
Logic Journal of the IGPL, 11(6):647-673.
Informal human
mathematical reasoning.
Jamnik, M. (2003)
AISB Quarterly, 114:3. Society for the Study of Artificial
Intelligence and Simulation of Behaviour.
Learning
strategies for mechanised building of decision
procedures.
Jamnik, M. and Janicic, P. (2003)
Electronic Notes in Theoretical Computer Science, 86(1):174-189.
Can decision
procedures be learnt automatically?
Jamnik, M. and Janicic, P. (2003)
In Dahn, I. and Vigneron, L., (eds.), Proceedings of the
4th International Workshop on First-order Theorem Proving,
FTP 2003, pages 35-48. Universidad Politecnica de
Valencia.
Automatic
learning in proof planning.
Jamnik, M., Kerber, M. and Pollet, M. (2002)
In van Harmelen, F., (ed.), Proceedings of 15th ECAI,
pages 282-286. European Conference on Artificial
Intelligence, IOS Press.
LearnOmatic:
System description.
Jamnik, M., Kerber, M. and Pollet, M. (2002)
In Voronkov, A., (ed.), 18th Conference on Automated
Deduction, number 2392 in Lecture Notes in Artificial
Intelligence, pages 150-155. Springer Verlag.
Using
animation in diagrammatic theorem proving.
Winterstein, D., Bundy, A., Gurr, C. and Jamnik,
M. (2002)
In Hegarty, M., Meyer, B. and Narayanan, H., (eds.),
Theory and Application of Diagrams: Second International
Conference, Diagrams 2002, Proceedings, number 2317 in
Lecture Notes in Artificial Intelligence, pages
46-60. Springer Verlag.
Mathematical
Reasoning with Diagrams: From Intuition to
Automation.
Jamnik, M. (2001)
CSLI Press, Stanford, CA, USA.
Agent
based mathematical reasoning.
Benzmueller, C., Jamnik, M., Kerber, M. and Sorge, V. (2001)
Electronic Notes in Theoretical Computer Science, 23(3):21-33.
Experiments with
an agent-oriented reasoning system.
Benzmueller, C., Jamnik, M., Kerber, M. and Sorge,
V. (2001)
In Baader, F., Brewka, G. and Eiter, T., (eds.),
Proceeding of the KI 2001: Advances in Artificial
Intelligence, number 2174 in Lecture Notes in Artificial
Intelligence, pages 409-424. Springer Verlag.
Towards
learning new methods in proof planning.
Jamnik, M., Kerber, M. and Benzmueller, C. (2001)
In Kerber, M. and Kohlhase, M., (eds.),
Symbolic Calculation and Automated Reasoning: The
Calculemus 2000 Symposium, pages 141-156, Natick,
MA. A K Peters.
Resource
guided concurrent deduction.
Benzmueller, C., Jamnik, M., Kerber, M. and Sorge, V. (2001)
In Kerber, M. and Kohlhase, M., (eds.), Symbolic
Calculation and Automated Reasoning: The Calculemus
2000 Symposium, pages 243-244, Natick, MA. A K Peters.
A proposal for automatic
diagrammatic reasoning in continuous
domains.
Winterstein, D., Bundy, A. and Jamnik, M. (2000)
In Anderson, M., Cheng, P. and Haarslev, V., (eds.), Theory
and Application of Diagrams: First International
Conference, Diagrams 2000, Proceedings, number 1889 in
Lecture Notes in Artificial Intelligence, pages
286-299. Springer Verlag.
Towards
learning new methods in proof planning.
Jamnik, M., Kerber, M. and Benzmueller, C. (2000)
In Colton, S., Martin, U. and Sorge, V., (eds.),
Proceedings of the CADE-17 Workshop on The Role of
Automated Deduction in Mathematics, pages 1-11. Also
appeared at Calculemus 2000.
Resource guided
concurrent deduction.
Benzmueller, C., Jamnik, M., Kerber, M. and Sorge, V. (2000)
In Sloman, A., (ed.), Proceedings of the AISB-2000
Workshop: How to Design a Functioning Mind,
pages 137-138. Society for the Study of Artificial
Intelligence and Simulation of Behaviour. Also appeared at
Calculemus 2000.
On
Automating Diagrammatic Proofs of Arithmetic
Arguments.
Jamnik, M., Bundy, A. and Green, I. (1999)
Journal of Logic, Language and
Information. 8(3):297-321.
Agent based mathematical reasoning.
Benzmueller, C., Jamnik, M., Kerber, M. and Sorge, V. (1999)
In Armando, A. and Jebelean, T., (eds.), Proceedings of
the FLOC 1999 Calculemus Workshop: Systems for Integrated
Computation and Deduction, pages 1-12. Conference on
Automated Deduction (CADE).
On Automating Diagrammatic Proofs of Arithmetic Arguments.
Jamnik, M. (1999)
Unpublished PhD thesis. Division of Informatics, University of
Edinburgh. 1999.
Verification
of Diagrammatic Proofs.
Jamnik, M., Bundy, A. and Green, I. (1998)
In Meyer, B., (ed.), Proceedings of the 1998 AAAI Fall
Symposium on Formalising Reasoning with Visual and
Diagrammatic Representations, pages 23-30. American
Association for Artificial Intelligence, AAAI
Press.
Automation
of Diagrammatic Reasoning.
Jamnik, M., Bundy, A. and Green, I. (1997)
In Pollack, M.E., (ed.), Proceedings of the 15th IJCAI,
vol. 1, pages 528-533. International Joint Conference on
Artificial Intelligence, Morgan Kaufmann Publishers. Also
published in the "Proceedings of the
1997 AAAI Fall
Symposium".
Automation
of Diagrammatic Proofs in Mathematics.
Jamnik, M., Bundy, A. and Green, I. (1997)
In Kokinov, B., (ed.), Perspectives on Cognitive Science,
vol. 3, pages 168-175. New Bulgarian University.