I'm a PhD student at the University of Oxford working with Michael Bronstein and Max Welling. My research focusses on the relationship between concepts in stochastic thermodynamics and generative Artificial Intelligence. Particularly I am interested in exploiting this relationship to build new methodologies to push the boundaries of applying Generative AI for problem in Computational and Biochemistry. Especially the computational challenge of Free-Energy Estimation.
I'm currently a Research Resident at Normal Computing in New York. Before starting my PhD I obtained a masters degree from the University of Amsterdam under the supervision of Max Welling and Yarin Gal as part of the ELLIS MSc program. Prior to this, I worked as student research at Porsche and obtained my bachelors degree in computer science from the University of Groningen. At the time my research primarily focussed on robust and interpretable machine learning.
[2025] L. Holdijk, NM. Anand, M. Bronstein, M. Welling, Learning Escorted Protocols for Multistate Free-Energy Estimation, International Conference on Learning Respresentations (ICLR'26)
[2023] L. Holdijk*, Y. Du*, F. Hooft, P. Jaini, B. Ensing, M. Welling, Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths, Advances in Neural Information Processing Systems (NeurIPS'23)
[2025] J. Lee, M. Plainer, Y, Du, L. Holdijk, R. Brekelmans, D. Beaini, K. Neklyudov, Scaling Deep Learning Solutions for Transition Path Sampling, ICLR'25 Fronties in Probabilistic Inference
[2024] L. Holdijk, M. Bronstein, M. Welling, Learning Protocols for Non-Equilibrium Conformational Free-Energy Estimation Using Optimal Transport and Conditional Flow Matching, NeurIPS2024 AIDrugX
[2021] L. Holdijk, M. Boon, S. Henckens, L. de Jong, [Re] Parameterized Explainer for Graph Neural Network. ReScience C.
(*: denotes equal contribution)