Full list of papers on Google Scholar.

Preprints

Analyzing the Posterior Collapse in Hierarchical Variational Autoencoders.
Anna Kuzina, Jakub M. Tomczak
Paper, Code.

Published papers

Alleviating Adversarial Attacks on Variational Autoencoders with MCMC.
Anna Kuzina, Max Welling, Jakub M. Tomczak
NeurIPS 2022.
Paper, Code.

On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models.
Anna Kuzina* and Kamil Deja*, Tomasz Trzcinski, Jakub M. Tomczak
* Equal contribution
NeurIPS 2022.
Paper, Code.

Equivariant Priors for Compressed Sensing with Unknown Orientation.
Anna Kuzina, Kumar Pratik, Fabio Valerio Massoli, Arash Behboodi
ICML 2022. \ Paper.

CKConv: Continuous Kernel Convolution For Sequential Data.
David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
ICLR 2022.
Paper, Code.

BooVAE: Boosting Approach for Continual Learning of VAE.
Anna Kuzina* and Evgenii Egorov*, Evgeny Burnaev
* Equal contribution
NeurIPS 2021.
Paper, Code.

Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks.
Anna Kuzina, Max Welling, Jakub M. Tomczak
ICLR 2021. RobustML Workshop
Paper, Code.

Bayesian generative models for knowledge transfer in MRI semantic segmentation problems.
Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
Frontiers in neuroscience, 2019
Paper, Code.

Posters and Presentations

Alleviating Adversarial Attacks on Variational Autoencoders with MCMC.
Poster on ProbAI Summer School 2022, Helsinki.
Poster.

Bayesian generative models for knowledge transfer in MRI semantic segmentation problems.
Poster on MIDL 2020, Online.
Slides, Video.

BooVAE: A scalable framework for continual VAE learning under boosting approach.
Spotlight on AABI 2019, Vancouver, Canada.
Poster.

MRI-based stroke outcome prediction and treatment planning.
Poster on Human Brain Project Conference 2019, Ghent, Belgium.
Poster.