Since April 2025, I am a FCAI Research Fellow at Aalto University, a 5-year position funded by the Finnish Center for Artificial Intelligence. I work with groups

• Computational Systems Biology (Prof. Harri Lähdesmäki)
• Probabilistic Machine Learning (Prof. Samuel Kaski)

I am also a member of the ELLIS AI network, affiliated with ELLIS Institute Finland.

My interests span:

• Biology-Informed Machine Learning: blending flexible data-driven approaches and mechanistic models within Systems Biology

$\rightarrow$ For more information, you can have a look to this position piece: Position: Biology is the Challenge Physics-Informed ML needs to Evolve

• Bayesian Optimization, in particular recently, in-context learning flavors, see e.g., our ICLR’26 paper or our recent preprint.

I obtained my PhD in February 2022 from Ecole polytechnique, Inria and Institut Curie, under the supervision of François Fages and Annabelle Ballesta. The manuscript can be found here and the slides here. A detailed CV can be found here (Last updated: May 2026).

Besides, for a few years now, I have been cultivating a passion for indoor bouldering, with a mild success thus far 🫠

News

Upcoming talks and posters:

• ISBA, June 29th, Nagoya: In-context multi-objective optimization (Poster session)

• ProbML 2026, July 5th, Seoul: Marshal Sinaga will present our work on Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimization.

• ICML, July 10-11th, Seoul: In-context learning for latent space bayesian optimiztion (EIML and DEMO Workshops, Poster sessions)

• ECMTB, July 14th, Graz: Bayesian discovery of biochemical reaction networks from time-course data with projection predictive inference (Contributed talk, part of a minisymposium on Automated discovery of dynamical digital twins from time series)

• ECTMB, July 16th, Graz: Learning Population Dynamical Models in Systems Biology with Mixed-Effect Gaussian Process ODEs (Poster session)

• Julie Bertrand will present our work on Joint Bayesian Inference of Genetic Effect Sizes and PK Parameters in Nonlinear Mixed-Effects Models at Stancon 2026

A paper accepted at ICML workshop on Epistemic Intelligence and Machine Learning!

• T. A. Vu, H. Lähdesmäki, J.M. In-Context Learning for Latent Space Bayesian Optimization. Stay tuned for camera-ready version!

A paper accepted at ProbML 2026!

• M. Sinaga, J.M., and S. Kaski. Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimization.

New work on Gaussian Process ODEs:

• J. M., M. Sinelnikov, H. Lähdesmäki, Q. Clairon, M. Prague Bayesian Nonparametric Mixed-Effect ODEs with Gaussian Processes. arXiv, 2026.

New work on Bayesian Optimization:

• M. Sinaga^°, J. M.^°, T. Turpeinen, and S. Kaski. Online Sharp-Calibrated Bayesian Optimization. arXiv, 2026.

New work on In-context optimization:

• N. Blumer, J. M., and S. Kaski. In-Context Black-Box Optimization with Unreliable Feedback. arXiv, 2026.