I am an Associate Professor (Universitair Hoofddocent) at the University of Amsterdam, where I direct the AMLab, co-direct the UvA Bosch Delta Lab, and direct the Amsterdam ELLIS Unit.

My research develops principled methods for generative AI and probabilistic inference, with a focus on methods for scalable and data-efficient scientific computation. This includes scalable neural architectures for physical systems, learned surrogate models, and deep generative models for molecular and materials design. A particular ongoing interest is variational flow matching — a framework that reformulates flow-based generative models through a variational lens, enabling principled approaches to discrete and structured data, controlled generation, and test-time conditioning. I collaborate closely with domain scientists in physical chemistry, fluid mechanics, and materials science.

Earlier in my career I worked extensively on probabilistic programming — designing languages and inference algorithms that allow researchers to express complex probabilistic models as programs. This led to the development of Anglican, foundational work on inference methods for universal probabilistic programs, and a textbook.

Prior to joining the University of Amsterdam, I was an Assistant Professor at Northeastern University. I carried out my PhD research in biophysics at Leiden and Cambridge with Wim van Saarloos and Ray Goldstein, and held postdoctoral positions with Frank Wood at Oxford and with Chris Wiggins and Ruben Gonzalez at Columbia. I was a founding co-chair of the international conference on probabilistic programming (PROBPROG) and a program chair for AISTATS 2023.

Current Students and Postdocs

Bob van Sluijs
Postdoctoral Researcher

Daniel Acuña Ramírez
Postdoctoral Researcher

Jacobus Dijkman
Ph.D. Candidate

Floor Eijkelboom
Ph.D. Candidate

Daan Roos
Ph.D. Candidate

Tin Hadži Veljković
Ph.D. Candidate

Max Zhdanov
Ph.D. Candidate

Alumni

• James Townsend (Postdoc, UvA) — Anthropic
• Heiko Zimmermann (Ph.D. 2025, UvA) — Research Scientist, Pasteur Labs
• Ondrej Bíža (Ph.D. 2024, Northeastern) — Research Scientist, RAI Institute
• Niklas Smedemark-Margulies (Ph.D. 2024, Northeastern) — Director of Bioinformatics Software Engineering, Variantyx
• Jered McInerney (Ph.D. 2024, Northeastern) — Data Scientist, CodaMetrix
• Eli Sennesh (Ph.D. 2023, Northeastern) — Postdoctoral Fellow, Vanderbilt University
• Hao Wu (Ph.D. 2023, Northeastern) — AWS
• Babak Esmaeili (Ph.D. 2023, UvA) — Postdoc, TU Eindhoven
• Robin Walters (Postdoc, Northeastern) — Assistant Professor, Northeastern University
• Silvio Amir (Postdoc, Northeastern) — Assistant Professor, Northeastern University

Recent Papers

A full list of publications can be found on Google Scholar.

1. MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention

   [arXiv] arXiv preprint , 2025

   Pedro M. P. Curvo, Jan-Willem van de Meent, Maksim Zhdanov

   [Link] [PDF]
2. Purrception: Variational Flow Matching for Vector-Quantized Image Generation

   [arXiv] arXiv preprint , 2025

   Răzvan-Andrei Matişan, Vincent Tao Hu, Grigory Bartosh, Björn Ommer, Cees G. M. Snoek, Max Welling, Jan-Willem van de Meent, Mohammad Mahdi Derakhshani, Floor Eijkelboom

   [Link] [PDF]
3. Discovering Lie Groups with Flow Matching

   [arXiv] arXiv preprint , 2025

   Jung Yeon Park, Yuxuan Chen, Floor Eijkelboom, Jan-Willem van de Meent, Lawson L. S. Wong, Robin Walters

   [Link] [PDF]
4. Controlled Generation with Equivariant Variational Flow Matching

   [ICML] International Conference on Machine Learning, 2025

   Floor Eijkelboom, Heiko Zimmermann, Erik Bekkers, Max Welling, Christian Naesseth, Jan-Willem van de Meent

   [Link] [PDF]
5. Exponential Family Variational Flow Matching for Tabular Data Generation

   [ICML] International Conference on Machine Learning, 2025

   Andrés Guzmán-Cordero, Floor Eijkelboom, Jan-Willem van de Meent

   [Link] [PDF]
6. Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems

   [ICML] International Conference on Machine Learning, 2025

   Maksim Zhdanov, Max Welling, Jan-Willem van de Meent

   [Link] [PDF] [Code]
7. On-Robot Reinforcement Learning with Goal-Contrastive Rewards

   [ICRA] IEEE International Conference on Robotics and Automation, 2025

   Ondrej Biza, Thomas Weng, Lingfeng Sun, Karl Schmeckpeper, Tarik Kelestemur, Yecheng Jason Ma, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong

   [Link] [PDF]
8. Learning Neural Free-Energy Functionals with Pair-Correlation Matching

   [PRL] Physical Review Letters , 2025

   Jacobus Dijkman, Marjolein Dijkstra, René van Roij, Max Welling, Jan-Willem van de Meent, Bernd Ensing

   [Link] [PDF]
9. Practical Shuffle Coding

   [NeurIPS] Advances in Neural Information Processing Systems, 2024

   Julius Kunze, Daniel Severo, Jan-Willem van de Meent, James Townsend

   [Link] [PDF] [Code]
10. Variational Flow Matching for Graph Generation

    [NeurIPS] Advances in Neural Information Processing Systems, 2024

    Floor Eijkelboom, Grigory Bartosh, Christian A. Naesseth, Max Welling, Jan-Willem van de Meent

    [Link] [PDF]
11. VISA: Variational Inference with Sequential Sample-Average Approximations

    [NeurIPS] Advances in Neural Information Processing Systems, 2024

    Heiko Zimmermann, Christian A. Naesseth, Jan-Willem van de Meent

    [Link] [PDF] [Code]
12. Towards Reducing Diagnostic Errors with Interpretable Risk Prediction

    [NAACL] Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2024

    Denis Jered McInerney, William Dickinson, Lucy C. Flynn, Andrea C. Young, Geoffrey S. Young, Jan-Willem van de Meent, Byron C. Wallace

    [Link] [PDF]
13. Entropy Coding of Unordered Data Structures

    [ICLR] International Conference on Learning Representations, 2024

    Julius Kunze, Daniel Severo, Giulio Zani, Jan-Willem van de Meent, James Townsend

    [Link] [PDF] [Code]

Selected Papers

1. Nested Variational Inference

   [NeurIPS] Advances in Neural Information Processing Systems, 2021

   Heiko Zimmermann, Hao Wu, Babak Esmaeili, Jan-Willem van de Meent

   [Link] [PDF]
2. Learning Proposals for Probabilistic Programs with Inference Combinators

   [UAI] Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2021

   Sam Stites, Heiko Zimmermann, Hao Wu, Eli Sennesh, Jan-Willem van de Meent

   [Link] [PDF] [Code]
3. Structured Disentangled Representations

   [AISTATS] International Conference on Artificial Intelligence and Statistics, 2019

   Babak Esmaeili, Hao Wu, Sarthak Jain, Alican Bozkurt, N. Siddharth, Brooks Paige, Dana H. Brooks, Jennifer Dy, Jan-Willem van de Meent

   [Link] [PDF]
4. Learning Disentangled Representations with Semi-Supervised Deep Generative Models

   [NeurIPS] Advances in Neural Information Processing Systems, 2017

   N. Siddharth, Brooks Paige, Jan-Willem van de Meent, Alban Desmaison, Noah D. Goodman, Pushmeet Kohli, Frank Wood, Philip Torr

   [Link] [PDF] [Code]
5. An Introduction to Probabilistic Programming

   [arXiv] arXiv preprint arXiv:1809.10756 , 2018

   Jan-Willem van de Meent, Brooks Paige, Hongseok Yang, Frank Wood

   [Link] [PDF]
6. Design and Implementation of Probabilistic Programming Language Anglican

   [IFL] Symposium on the Implementation and Application of Functional Programming Languages, 2016

   David Tolpin, Jan-Willem van de Meent, Hongseok Yang, Frank Wood

   [Link] [PDF] [Code]
7. A New Approach to Probabilistic Programming Inference

   [AISTATS] International Conference on Artificial Intelligence and Statistics, 2014

   Frank Wood, Jan-Willem van de Meent, Vikash Mansinghka

   [Link] [PDF] [Code]