Jakub M. Tomczak



Scientist & AI Specialist

Jakub M. Tomczak is an assistant professor of Artificial Intelligence in the Computational Intelligence group (led by Prof. A.E. Eiben) at Vrije Universiteit Amsterdam. Before joining Vrije Universiteit Amsterdam, he was a deep learning researcher (Engineer, Staff) in Qualcomm AI Research in Amsterdam, a Marie Sklodowska-Curie individual fellow in Prof. Max Welling's group at the University of Amsterdam, and an assistant professor and postdoc at the Wroclaw University of Technology. His main research interests include deep generative modeling, deep learning, and Bayesian inference, with applications to image processing, robotics, and life sciences. He is the author of the book entitled "Deep Generative Modeling".


Years of Experience

Supervised projects

Top publications

Funding gathered (EUR)



Ph.D. in Computer Science (Machine Learning)

Mar 2013

Wroclaw University of Technology, Poland

Title: Incremental Knowledge Extraction from Data for Non-Stationary Objects

Supervisor: Prof. Jerzy Swiatek

M.Sc. in Computer Science

Dec 2009

Blekinge Institute of Technology, Sweden

M.Sc. in Computer Science

Jul 2009

Wroclaw University of Technology, Poland

Work Experience


Mar 2022 - Present

NatInLab, Amsterdam, the Netherlands

Assistant Professor of Artificial Intelligence

Nov 2019 - present

Vrije Unviersiteit Amsterdam, the Netherlands

Deep Learning Researcher (Staff Engineer)

Oct 2018 - Dec 2019

Qualcomm AI Research, Amsterdam, the Netherlands

Postdoc/Marie Sklodowska-Curie Individual Fellow

Oct 2016 - Sept 2018

Universiteit van Amsterdam, the Netherlands

Researcher (part-time)

Feb 2016 - Jun 2016

INDATA SA, Wroclaw. Poland

Assistant Professor

Oct 2014 - Sept 2016

Wroclaw University of Technology. Poland


Oct 2012 - Sept 2014

Wroclaw University of Technology. Poland

Ph.D. student / Research assistant

Jun 2009 - Sept 2012

Wroclaw University of Technology. Poland



J.M. Tomczak, ''Deep Generative Modeling'', Springer, Cham, 2022.

Conference Papers

D.W. Romero, R.-J. Bruintjes, J.M. Tomczak, E.J. Bekkers, M. Hoogendoorn, J. van Gemert, Flexconv: Continuous kernel convolutions with differentiable kernel sizes, ICLR, 2022

D.W. Romero, A. Kuzina, E.J. Bekkers, J.M. Tomczak, M. Hoogendoorn, CKCONV: Continuous kernel convolution for sequential data, ICLR, 2022

E. Krieken, J.M. Tomczak, A. ten Teije, Storchastic: A Framework for General Stochastic Automatic Differentiation, NeurIPS, 2021

Y. Perugachi-Diaz, J.M. Tomczak, S. Bhulai, Invertible DenseNets with concatenated Lipswish, NeurIPS, 2021

M. Ilse, J.M. Tomczak, P. Forre, Selecting data augmentation for simulating interventions, ICML 2021

D.W. Romero, E.J. Bekkers, J.M. Tomczak, M. Hoogendoorn, Attentive group equivariant convolutional networks, ICML 2020

E. Hoogeboom, V. Garcia Satorras, J.M. Tomczak, M. Welling, The convolution exponential and generalized sylvester flows, NeurIPS 2020

J.M. Tomczak, E. Weglarz-Tomczak, A.E. Eiben, Differential evolution with reversible linear transformations, GECCO 2020

M. Ilse, J.M. Tomczak, C. Louizos, M. Welling, DIVA: Domain invariant variational autoencoders, MIDL 2020

D. Abati, J.M. Tomczak, T. Blankevoort, S. Calderara, R. Cucchiara, B. Ehteshami Bejnordi, Conditional Channel Gated Networks for Task-Aware Continual Learning, CVPR, 2020

I. Gatopoulos, R. Lepert, A. Wiggers, G. Mariani, J.M. Tomczak, Evolutionary Algorithm with Non-parametric Surrogate Model for Tensor Program Optimization, IEEE CEC 2020

CY. Oh, J.M. Tomczak, E. Gavves, M. Welling, Combinatorial Bayesian Optimization using the Graph Cartesian Product, NeurIPS, Vancouver, Canada, 2019

A. Habibian, T. van Rozendaal, J.M. Tomczak, T.S. Cohen, Video compression with rate-distortion autoencoders, ICCV, Seol, South Korea, 2019

T. Davidson, L. Falorsi, N. de Cao, T. Kipf, J.M. Tomczak, Hyperspherical Variational Auto-Encoders, UAI, Monterey, California, the USA, 2018

R. van den Berg, L. Hasenclever, J.M. Tomczak, M. Welling, Sylvester Normalizing Flow for Variational Inference, UAI, Monterey, California, the USA, 2018

M. Ilse*, J.M. Tomczak*, M. Welling, Attention-based Deep Multiple Instance Learning, ICML, Stockholm, Sweden, 2018

J.M. Tomczak, M. Welling, VAE with a VampPrior, AISTATS, the Canary Islands, 2018

J.M. Tomczak, M. Welling, Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow, Benelearn 2017, Eindhoven, the NL, 2017

J.M. Tomczak, M.Welling, Improving Variational Auto-Encoders using Householder Flow, NIPS Workshop on Bayesian Deep Learning, Barcelona, Spain, 2016

Journal articles

J. Luo, A. Stuurman, J.M. Tomczak, J. Ellers, A.E. Eiben, The Effects of Learning in Morphologically Evolving Robot Systems, Frontiers in Robotics and AI, 2022

G. Lan, J.M. Tomczak, D.M. Roijers, A.E. Eiben., Time efficiency in optimization with a bayesian-evolutionary algorithm, Swarm and Evolutionary Computation, 2022

F. Lavitt, D.J. Rijlaarsdam, D. van der Linden, E. Weglarz-Tomczak, J.M.Tomczak, Deep learning and transfer learning for automatic cell counting in microscope images of human cancer cell lines, Applied Sciences, 2021

G. Lan, M. van Hooft, M. De Carlo, J.M.Tomczak, A.E. Eiben, Learning locomotion skills in evolvable robots, Neurocomputing, 2021 \item Y. Perugachi-Diaz, J.M. Tomczak, S. Bhulai, Deep learning for white cabbage seedling prediction, Computers and Electronics in Agriculture, 2021

E. Weglarz-Tomczak, J.M. Tomczak, M. Talma, M. Burda-Grabowska, M. Giurg, S. Brul, Identification of ebselen and its analogues as potent covalent inhibitors of papain-like protease from SARS-CoV-2, Scientific Reports, 2021

I.A. Auzina, J.M. Tomczak, Approximate bayesian computation for discrete spaces, Entropy, 2021

I. Gatopoulos, J.M. Tomczak, Self-supervised variational auto-encoders, Entropy, 2021

E. Weglarz-Tomczak, J.M. Tomczak, S. Brul, M2R: a Python add-on to cobrapy for modifying human genome-scale metabolic reconstruction using the gut microbiota models, Bioinformatics, 2021

E. Weglarz-Tomczak, D.J. Rijlaarsdam, J.M. Tomczak, S. Brul, GEM-based metabolic profiling for Human Bone Osteosarcoma under different glucose and glutamine availability, International Journal of Molecular Sciences 22 (3), 1470, 2021

E. Weglarz-Tomczak, J.M. Tomczak, A.E. Eiben, S. Brul, Population-Based Parameter Identification for Dynamical Models of Biological Networks with an Application to Saccharomyces cerevisiae, Processes 9 (1), 98, 2021

J.M. Tomczak, E. Weglarz-Tomczak, Estimating kinetic constants in the Michaelis‐Menten model from one enzymatic assay using Approximate Bayesian Computation, FEBS Letters, 2019

J.M. Tomczak, S. Zareba, S. Ravanbakhsh, R. Greiner, Low-Dimensional Perturb-and-MAP Approach for Learning Restricted Boltzmann Machines, Neural Processing Letters, 2017

M. Drewniak, E. Weglarz-Tomczak, K. Ozga, E. Rudzinska-Szostak, K. Macegoniuk, J.M. Tomczak, M. Bejger, W. Rypniewski, L. Berlicki, Helix-loop-helix peptide foldamers and their use in the construction of hydrolase mimetics, Bioorganic Chemistry, Vol. 81, pp. 356--361

A. Gonczarek, J.M. Tomczak, S. Zareba, J. Kaczmar, P. Dabrowski, M. Walczak, Interaction prediction in structure-based virtual screening using deep learning, Computers in Biology and Medicine, 2017

M. Zieba, S. Tomczak, J.M. Tomczak, Ensemble Boosted Trees with Synthetic Features Generation in Application to Bankruptcy Prediction, Expert Systems with Applications, Vol. 58, pp. 593--101, 2016

J.M. Tomczak, On some properties of the low-dimensional Gumbel perturbations in the Perturb-and-MAP model, Statistics and Probability Letters, 2016

J.M. Tomczak, A. Gonczarek, Learning invariant features using Subspace Restricted Boltzmann Machine, Neural Processing Letters, 2016

A. Gonczarek, J.M. Tomczak, Articulated tracking with manifold regularized particle filter, Machine Vision and Applications, Volume 27, Issue 2, pp 275--286

J.M. Tomczak, Learning Informative Features from Restricted Boltzmann Machines, Neural Processing Letters

J.M. Tomczak, M. Zieba, Probabilistic combination of classification rules and its application to medical diagnosis, Machine Learning, Vol. 101, Issue 1, pp. 105-135

J.M. Tomczak, M. Zieba, Classification Restricted Boltzmann Machine for comprehensible credit scoring model, Expert Systems with Applications, Volume 42, Issue 4, March 2015

M. Zieba, J.M. Tomczak, Boosted SVM with active learning strategy for imbalanced data, Soft Computing, August 2014, Pages 99--108

M. Zieba, J.M. Tomczak, J. Swiatek, M. Lubicz, Boosted SVM for extracting rules from imbalanced data in application to prediction of the post-operative life expectancy in the lung cancer patients, Applied Soft Computing, Volume 14, Part A, January 2014, Pages 99--108

J.M. Tomczak, A. Gonczarek, Decision rules extraction from data stream in the presence of changing context for diabetes treatment, Knowledge and Information Systems, 2013, Vol. 34, Issue 3, pp. 521--546

Additional Information


Collaborators, PhD students, MSc students, and former students


My presentations at conferences, workshops, for academic and industrial research groups, summer schools


My project that was carried out from 2016/10/1 to 2018/09/30 within the Marie Skłodowska-Curie Action (Individual Fellowship), financed by the European Comission.


Courses, teaching activities, supervision, and my teaching qualifications


  • All
  • VAEs
  • GANs
  • Flows
  • ARMs
  • Joint
  • Theory
  • Applications


- Why do we need deep generative modeling?
- Where do we use deep generative modeling?
- How do we formulate deep generative models?

Autoregressive Models

- What is an autoregressive model.
- How we can parameterize an autoregressive model using various neural networks.
- How to implement your own autoregressive model using causal convolutions!

Flow-based Models

- What is a flow-based model.
- How we can parameterize a flow-based model using invertible neural networks.
- How to implement your own flow-based model using coupling layers!

Variational Auto-Encoders

- What is a latent variable model.
- How we can learn non-linear latent variable models with variational inference.
- How to implement your own Variational Auto-Encoder!

Integer Discrete Flows

- What is a potential problem with continous variables.
- How we can learn a distribution over integer-valued variables.
- How to implement your own Integer Discrete Flows!

Hybrid modeling

- How to train the joint distribution p(x,y).
- How we can make it work.
- How to implement your own hybrid model with IDFs!

Priors in VAEs

- How to re-write the ELBO in VAEs.
- Why priors are so important.
- How to model priors using Mixture of Gaussians, VampPriors, GTMs and flows!

Neural Compression

- What is image compression.
- What is neural compression.
- How to use deep generetive modeling for neural compression

Hierarchical VAEs

- Why we use hierarchical latent variable models.
- How to construct hierarchical VAEs.
- How to implement top-down VAEs.

Diffusion-based Models

- How to construct hierarchical VAEs with duffiusion-based encoders.
- How to implement diffusion-based DGMS.
- What are recent developments in diffusion-based DGMs.

Energy-based Models

- How to construct an energy-based model.
- How to implement the Langevin dynamics.
- What are the potential problems with these models.


- What are density networks.
- How to formulate the adversarial optimization problem.
- How to implement GANs.

Trouble in Paradise

- What is the problem with variational inference.
- Are Latent Variable Models good for representation learning?

Are we dil(ff)usional?!

- What is the ELBO for diffusion-based models.
- What are the consequences of applying diffusion to the ELBO?



De Boelelaan 1111, 1081 HV, Amsterdam, the Netherlands