Preprints

X. Zhang, C. Hassan, J. Martinelli, D. Huang, and S. Kaski. Task-Agnostic Amortized Multi-Objective Optimization. OpenReview, 2025

C. Métayer, A. Ballesta, and J. Martinelli. Data-driven Discovery of Digital Twins in Biomedical Research. arXiv, 2025

M. Sinaga, J. Martinelli, V. Garg, and S. Kaski. Heteroscedastic Preferential Bayesian Optimization with Informative Noise Distributions. arXiv, 2024

J. Martinelli, J. Grignard, S. Soliman, A. Ballesta, and F. Fages. Reactmine: a statistical search algorithm for inferring chemical reactions from time series data arXiv, 2022

Publications

J. Martinelli. Position: Biology is the Challenge Physics-Informed ML needs to Evolve. NeurIPS, 2025 (6% Acceptance rate)

M. Sinaga, J. Martinelli, and S. Kaski. Robust and Computation-Aware Gaussian Processes, NeurIPS, 2025

S. Sloman, J. Martinelli, and S. Kaski. Proxy-informed Bayesian transfer learning with unknown sources. UAI, 2025

X. Zhang, D. Huang, S. Kaski, and J. Martinelli. PABBO: Preferential Amortized Black-Box Optimization. ICLR, 2025 (Spotlight)

Y. Nahal, J. Menke, J. Martinelli, M. Heinonen, M. Kabeshov, J. J. Paul, E. Nittinger, O. Engkvist, and S. Kaski. Human-in-the-loop active learning for goal-oriented molecule generation. Journal of Cheminformatics, 2024

S. Sloman, A. Bharti, J. Martinelli, and S. Kaski. Bayesian Active Learning in the Presence of Nuisance Parameters. UAI, 2024 (Oral)

J. Martinelli, A. Bharti, A. Tiihonen, S. T. John, L. Filstroff, S. Sloman, P. Rinke, and S. Kaski. Learning relevant contextual variables within Bayesian Optimization. UAI, 2024

C. Frioux, S. Huet, S. Labarthe, J. Martinelli, T. Malou, D. Sherman, M.-L. Taupin, and P. Ugalde-Salas. Accelerating metabolic models evaluation with statistical metamodels: application to Salmonella infection models. ESAIM: Proceedings and Surveys, 2023

P. Mikkola, J. Martinelli, L. Filstroff, and S. Kaski. Multi-Fidelity Bayesian Optimization with Unreliable Information Sources. AISTATS, 2023

J. Martinelli, J. Hesse, O. Aboumanify, A. Ballesta, and Â. Relógio. A mathematical model of the circadian clock and drug pharmacology to optimize irinotecan administration timing in colorectal cancer. Computational and Structural Biotechnology Journal, 2021

J. Martinelli, S. Dulong, X.-M. Li, M. Teboul, S. Soliman, F. Lévi, F. Fages, and A. Ballesta. Model learning to identify systemic regulators of the peripheral circadian clock. Bioinformatics, 2021

J. Martinelli, J. Grignard, S. Soliman, and F. Fages. On inferring reactions from data time series by a statistical learning greedy heuristics. International Conference on Computational Methods in Systems Biology (CMSB), 2019

Workshop Communications

X. Zhang, J. Martinelli, and S. T. John. Challenges in interpretability of additive models. IJCAI 2024 Workshop on Explainable Artificial Intelligence (XAI), 2024

J. Martinelli, Y. Nahal, D. Lê, O. Engkvist, and S. Kaski. Leveraging expert feedback to align proxy and ground truth rewards in goal-oriented molecular generation. NeurIPS 2023 Workshop on New Frontiers of AI for Drug Discovery and Development, 2023

M. Sinaga, J. Martinelli, and S. Kaski. Preferential Heteroscedastic Bayesian Optimization with Informative Noise Priors NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World (RealML-2023), 2023

J. Martinelli, J. Grignard, S. Soliman, and F. Fages. A statistical unsupervised learning algorithm for inferring reaction networks from time series data. ICML 2019 Workshop on Computational Biology, 2019

PhD Thesis

J. Martinelli. On learning mechanistic models from time series data with applications to personalised chronotherapies. Ph.D. Thesis, École Polytechnique, 2022