Kamil Deja

50 papers A* 4A 4B 1Misc 1Journal 37Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
ELROND: Exploring and decomposing intrinsic capabilities of diffusion models.
CoRR
Pawel Skiers, Tomasz Trzcinski, Kamil Deja
2026 J jnl
TADA! Tuning Audio Diffusion Models through Activation Steering.
CoRR
Lukasz Staniszewski, Katarzyna Zaleska, Mateusz Modrzejewski, Kamil Deja
2025 J jnl
Adapt & Align: Continual Learning with Generative Models' Latent Space Alignment.
Neurocomputing
Kamil Deja, Bartosz Cywinski, Jan Rybarczyk, Tomasz Trzcinski
2025 A conf
ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts.
ECAI
Patryk Bedkowski, Jan Dubinski, Filip Szatkowski, Kamil Deja, Przemyslaw Rokita, Tomasz Trzcinski
2025 J jnl
ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts.
CoRR
Patryk Bedkowski, Jan Dubinski, Filip Szatkowski, Kamil Deja, Przemyslaw Rokita, Tomasz Trzcinski
2025 A conf
GUIDE: Guidance-Based Incremental Learning with Diffusion Models.
ECAI
Bartosz Cywinski, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski, Lukasz Kucinski
2025 J jnl
JointDiffusion: Joint representation learning for generative, predictive, and self-explainable AI in healthcare.
Comput. Medical Imaging Graph.
Joanna Kaleta, Pawel Skiers, Jan Dubinski, Przemyslaw Korzeniowski, Tomasz Trzcinski, Jakub M. Tomczak, Kamil Deja
2025 J jnl
Membership and Dataset Inference Attacks on Large Audio Generative Models.
CoRR
Jakub Proboszcz, Pawel Kochanski, Karol Korszun, Donato Crisostomi, Giorgio Strano, Emanuele Rodolà, Kamil Deja, Jan Dubinski
2025 A* conf
Precise Parameter Localization for Textual Generation in Diffusion Models.
ICLR
Lukasz Staniszewski, Bartosz Cywinski, Franziska Boenisch, Kamil Deja, Adam Dziedzic
2025 J jnl
Precise Parameter Localization for Textual Generation in Diffusion Models.
CoRR
Lukasz Staniszewski, Bartosz Cywinski, Franziska Boenisch, Kamil Deja, Adam Dziedzic
2025 A* conf
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders.
ICML
Bartosz Cywinski, Kamil Deja
2025 J jnl
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders.
CoRR
Bartosz Cywinski, Kamil Deja
2025 J jnl
Variance-Covariance Regularization Improves Continual Learning.
IEEE Access
Piotr Hondra, Daniel Marczak, Kamil Deja
2024 J jnl
Deep Generative Models for Proton Zero Degree Calorimeter Simulations in ALICE, CERN.
CoRR
Patryk Bedkowski, Jan Dubinski, Kamil Deja, Przemyslaw Rokita
2024 J jnl
GUIDE: Guidance-based Incremental Learning with Diffusion Models.
CoRR
Bartosz Cywinski, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski, Lukasz Kucinski
2024 J jnl
Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN.
CoRR
Mikolaj Kita, Jan Dubinski, Przemyslaw Rokita, Kamil Deja
2024 J jnl
Joint Diffusion models in Continual Learning.
CoRR
Pawel Skiers, Kamil Deja
2024 J jnl
Looking Through the Past: Better Knowledge Retention for Generative Replay in Continual Learning.
IEEE Access
Valeriya Khan, Sebastian Cygert, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski
2024 J jnl
Low-Rank Continual Personalization of Diffusion Models.
CoRR
Lukasz Staniszewski, Katarzyna Zaleska, Kamil Deja
2024 J jnl
Machine-learning-based particle identification with missing data.
CoRR
Milosz Kasak, Kamil Deja, Maja Karwowska, Monika Jakubowska, Lukasz Graczykowski, Malgorzata Janik
2024 J jnl
Mediffusion: Joint Diffusion for Self-Explainable Semi-Supervised Classification and Medical Image Generation.
CoRR
Joanna Kaleta, Pawel Skiers, Jan Dubinski, Przemyslaw Korzeniowski, Kamil Deja
2024 J jnl
Particle identification with machine learning from incomplete data in the ALICE experiment.
CoRR
Maja Karwowska, Lukasz Graczykowski, Kamil Deja, Milosz Kasak, Malgorzata Janik
2024 J jnl
Particle physics DL-simulation with control over generated data properties.
CoRR
Karol Rogozinski, Jan Dubinski, Przemyslaw Rokita, Kamil Deja
2024 J jnl
There and Back Again: On the relation between noises, images, and their inversions in diffusion models.
CoRR
Lukasz Staniszewski, Lukasz Kucinski, Kamil Deja
2023 J jnl
Adapt & Align: Continual Learning with Generative Models Latent Space Alignment.
CoRR
Kamil Deja, Bartosz Cywinski, Jan Rybarczyk, Tomasz Trzcinski
2023 J jnl
Bayesian Flow Networks in Continual Learning.
CoRR
Mateusz Pyla, Kamil Deja, Bartlomiej Twardowski, Tomasz Trzcinski
2023 A conf
Diffusion-based accent modelling in speech synthesis.
INTERSPEECH
Kamil Deja, Georgi Tinchev, Marta Czarnowska, Marius Cotescu, Jasha Droppo
2023 J jnl
Exploring Continual Learning of Diffusion Models.
CoRR
Michal Zajac, Kamil Deja, Anna Kuzina, Jakub M. Tomczak, Tomasz Trzcinski, Florian Shkurti, Piotr Milos
2023 — conf
Learning Data Representations with Joint Diffusion Models.
ECML/PKDD (2)
Kamil Deja, Tomasz Trzcinski, Jakub M. Tomczak
2023 J jnl
Learning Data Representations with Joint Diffusion Models.
CoRR
Kamil Deja, Tomasz Trzcinski, Jakub M. Tomczak
2023 J jnl
Looking through the past: better knowledge retention for generative replay in continual learning.
CoRR
Valeriya Khan, Sebastian Cygert, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski
2023 J jnl
Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN.
CoRR
Jan Dubinski, Kamil Deja, Sandro Wenzel, Przemyslaw Rokita, Tomasz Trzcinski
2023 Misc conf
Modelling Low-Resource Accents Without Accent-Specific TTS Frontend.
ICASSP
Georgi Tinchev, Marta Czarnowska, Kamil Deja, Kayoko Yanagisawa, Marius Cotescu
2023 J jnl
Modelling low-resource accents without accent-specific TTS frontend.
CoRR
Georgi Tinchev, Marta Czarnowska, Kamil Deja, Kayoko Yanagisawa, Marius Cotescu
2022 A conf
Automatic Evaluation of Speaker Similarity.
INTERSPEECH
Kamil Deja, Ariadna Sánchez, Julian Roth, Marius Cotescu
2022 J jnl
Automatic Evaluation of Speaker Similarity.
CoRR
Kamil Deja, Ariadna Sánchez, Julian Roth, Marius Cotescu
2022 J jnl
Logarithmic Continual Learning.
IEEE Access
Wojciech Masarczyk, Pawel Wawrzynski, Daniel Marczak, Kamil Deja, Tomasz Trzcinski
2022 J jnl
Logarithmic Continual Learning.
CoRR
Wojciech Masarczyk, Pawel Wawrzynski, Daniel Marczak, Kamil Deja, Tomasz Trzcinski
2022 A* conf
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning.
IJCAI
Kamil Deja, Pawel Wawrzynski, Wojciech Masarczyk, Daniel Marczak, Tomasz Trzcinski
2022 A* conf
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models.
NeurIPS
Kamil Deja, Anna Kuzina, Tomasz Trzcinski, Jakub M. Tomczak
2022 J jnl
On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models.
CoRR
Kamil Deja, Anna Kuzina, Tomasz Trzcinski, Jakub M. Tomczak
2022 — conf
Selectively Increasing the Diversity of GAN-Generated Samples.
ICONIP (1)
Jan Dubinski, Kamil Deja, Sandro Wenzel, Przemyslaw Rokita, Tomasz Trzcinski
2022 J jnl
Selectively increasing the diversity of GAN-generated samples.
CoRR
Jan Dubinski, Kamil Deja, Sandro Wenzel, Przemyslaw Rokita, Tomasz Trzcinski
2021 B conf
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning.
IJCNN
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
2021 J jnl
End-to-End Sinkhorn Autoencoder With Noise Generator.
IEEE Access
Kamil Deja, Jan Dubinski, Piotr Nowak, Sandro Wenzel, Przemyslaw Spurek, Tomasz Trzcinski
2021 J jnl
Multiband VAE: Latent Space Partitioning for Knowledge Consolidation in Continual Learning.
CoRR
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
2021 — conf
On Robustness of Generative Representations Against Catastrophic Forgetting.
ICONIP (6)
Wojciech Masarczyk, Kamil Deja, Tomasz Trzcinski
2021 J jnl
On robustness of generative representations against catastrophic forgetting.
CoRR
Wojciech Masarczyk, Kamil Deja, Tomasz Trzcinski
2020 J jnl
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning.
CoRR
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
2020 J jnl
End-to-end Sinkhorn Autoencoder with Noise Generator.
CoRR
Kamil Deja, Jan Dubinski, Piotr Nowak, Sandro Wenzel, Tomasz Trzcinski