Jonathan Crabbé

Jonathan Crabbé

PhD Researcher

University of Cambridge


I am currently working towards my PhD thesis in the van der Schaar lab, a leading machine learning (ML) lab from the University of Cambridge led by Mihaela van der Schaar. In this stimulating environment, I am learning to become a well-rounded AI researcher.

We are gradually entering in a phase where humans will increasingly interact with AIs, hence forming human-AI teams. I see an immense potential in these teams to approach cutting-edge scientific and medical problems. My research focuses on making these teams more efficient by improving the information flow between complex ML models and human users. This touches upon various subjects of the AI literature, including ML Interpretability, Representation Learning and Data-Centric AI. In some sense, my goal is to build this microscope that would allow human beings to look inside a machine learning model. Through the interface of this microscope, human beings could rigorously validate ML models extract knowledge from them.

Download my resumé.

  • ML for Science and Healthcare
  • Interpretability
  • Representation Learning
  • Robust ML
  • Data-Centric AI
  • PhD in Applied Mathematics, 2020-2024

    University of Cambridge

  • MASt in Applied Mathematics, 2018-2019

    University of Cambridge

  • M1 in Physics, 2017-2018

    Ecole Normale Supérieure Paris

  • Bachelor in Engineering, 2014-2017

    Université Libre de Bruxelles



Implementation of SOTA ML (Pytorch, Pandas, Numpy, Scikit-Learn)

Mathematical Modelling

Strong mathematical background, my publications have strong theoretical components


Presentation of my research at many prestigious venues (NeurIPS, ICML)

Team Working

50% of my publications are the result of collaborative work


50% of my publications are the result of autonomous work


Supervision of several MPhil and PhD students, creation of pedagogical YouTube videos


PhD Researcher
Oct 2020 – Present Cambridge, UK
  • Conducted research in various sub-fields of machine learning.
  • Published several papers in top-tier conferences (NeurIPS, ICML).
  • Supervised the research of several MPhil/PhD students.
Quantitative Research Intern
Jun 2022 – Sep 2022 London, UK
  • Conducted research in machine learning applied to quantitative finance.
  • Learned to turn raw financial data into predictive features.
  • Presented findings in front of quant managers.
Research Intern
Oct 2019 – Oct 2020 Bruxelles, BE
  • Conducted research in black holes physics.
  • Created several pedagogical videos to help young students with maths and physics.
  • Responsible of physics example classes for first year pharma students.
Research Intern
Feb 2018 – Jul 2018 London, UK
  • Conducted research in quantum field theory and cosmology.
  • Implemented numerical solver for simulating the evolution of a toy cosmological model.
  • Demonstrated the emergence of a new type of singularity called caustics.


PhD Fellowship
Full PhD funding (tuition and maintenance).
Research Assistant Fellowship
Funding for a year of research.
Jennings Price
Awarded based on outstanding results for my MASt.
Awarded based on academic excellence.

Recent Publications

Quickly discover relevant content by filtering publications.
(2022). Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data. In NeurIPS 2022.

Cite Project

(2022). Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability. NeurIPS 2022 Datasets and Benchmarks Track.

PDF Cite Project Project

(2022). Label-Free Explainability for Unsupervised Models. In ICML 2022.

PDF Cite Code Project Project

(2022). Data-SUITE: Data-centric identification of in-distribution incongruous examples. In ICML 2022.

PDF Cite Project

(2022). DAUX: a Density-based Approach for Uncertainty eXplanations. In ICML 2022 DFUQ Workshop.

PDF Cite Project Project

(2021). Explaining Latent Representations with a Corpus of Examples. In NeurIPS 2021.

PDF Cite Code Project Video

(2021). Explaining Time Series Predictions with Dynamic Masks. In ICML 2021.

PDF Cite Code Project Video

(2020). Learning outside the black-box: the pursuit of interpretable models. In NeurIPS 2020.

PDF Cite Code Project Video