Bartlomiej Twardowski

81 papers A* 12A 6Misc 1Journal 47Unranked 15

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification. CoRR Dipam Goswami, Simone Magistri, Gido M. van de Ven, Bartlomiej Twardowski, Andrew D. Bagdanov, Tinne Tuytelaars, Joost van de Weijer
2026	J	`jnl`	IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment. CoRR Simone Magistri, Dipam Goswami, Marco Mistretta, Bartlomiej Twardowski, Joost van de Weijer, Andrew D. Bagdanov
2026	—	`conf`	Realistic Evaluation of Test-Time Adaptation: Unsupervised Model Selection. VISAPP (1) Sebastian Cygert, Damian Sójka, Tomasz Trzcinski, Bartlomiej Twardowski
2025	J	`jnl`	Accurate and Efficient Low-Rank Model Merging in Core Space. CoRR Aniello Panariello, Daniel Marczak, Simone Magistri, Angelo Porrello, Bartlomiej Twardowski, Andrew D. Bagdanov, Simone Calderara, Joost van de Weijer
2025	J	`jnl`	Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning. CoRR Stanislaw Pawlak, Bartlomiej Twardowski, Tomasz Trzcinski, Joost van de Weijer
2025	J	`jnl`	Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses. CoRR Stanislaw Pawlak, Jan Dubinski, Daniel Marczak, Bartlomiej Twardowski
2025	A	`conf`	GUIDE: Guidance-Based Incremental Learning with Diffusion Models. ECAI Bartosz Cywinski, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski, Lukasz Kucinski
2025	A*	`conf`	Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers. ICML Filip Szatkowski, Yaoyue Zheng, Fei Yang, Tomasz Trzcinski, Bartlomiej Twardowski, Joost van de Weijer
2025	A*	`conf`	No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces. ICML Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2025	J	`jnl`	No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces. CoRR Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2025	J	`jnl`	Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models. CoRR Dipam Goswami, Liying Wang, Bartlomiej Twardowski, Joost van de Weijer
2025	A*	`conf`	The Art of Deception: Color Visual Illusions and Diffusion Models. CVPR Alexandra Gomez-Villa, Kai Wang, C. Alejandro Párraga, Bartlomiej Twardowski, Jesus Malo, Javier Vazquez-Corral, Joost van de Weijer
2024	A	`conf`	AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation. BMVC Damian Sójka, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert
2024	J	`jnl`	Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning. CoRR Filip Szatkowski, Fei Yang, Bartlomiej Twardowski, Tomasz Trzcinski, Joost van de Weijer
2024	A	`conf`	Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning. WACV Filip Szatkowski, Mateusz Pyla, Marcin Przewiezlikowski, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
2024	J	`jnl`	Augmentation-aware self-supervised learning with conditioned projector. Knowl. Based Syst. Marcin Przewiezlikowski, Mateusz Pyla, Bartosz Zielinski, Bartlomiej Twardowski, Jacek Tabor, Marek Smieja
2024	—	`conf`	Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers. CVPR Workshops Dipam Goswami, Bartlomiej Twardowski, Joost van de Weijer
2024	J	`jnl`	Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers. CoRR Dipam Goswami, Bartlomiej Twardowski, Joost van de Weijer
2024	—	`conf`	Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery. ECCV (11) Grzegorz Rypesc, Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2024	J	`jnl`	Covariances for Free: Exploiting Mean Distributions for Federated Learning with Pre-Trained Models. CoRR Dipam Goswami, Simone Magistri, Kai Wang, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2024	A*	`conf`	Divide and not forget: Ensemble of selectively trained experts in Continual Learning. ICLR Grzegorz Rypesc, Sebastian Cygert, Valeriya Khan, Tomasz Trzcinski, Bartosz Zielinski, Bartlomiej Twardowski
2024	J	`jnl`	Divide and not forget: Ensemble of selectively trained experts in Continual Learning. CoRR Grzegorz Rypesc, Sebastian Cygert, Valeriya Khan, Tomasz Trzcinski, Bartosz Zielinski, Bartlomiej Twardowski
2024	—	`conf`	Exemplar-Free Continual Representation Learning via Learnable Drift Compensation. ECCV (7) Alex Gomez-Villa, Dipam Goswami, Kai Wang, Andrew D. Bagdanov, Bartlomiej Twardowski, Joost van de Weijer
2024	J	`jnl`	Exemplar-free Continual Representation Learning via Learnable Drift Compensation. CoRR Alex Gomez-Villa, Dipam Goswami, Kai Wang, Andrew D. Bagdanov, Bartlomiej Twardowski, Joost van de Weijer
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`	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	—	`conf`	MAGMAX: Leveraging Model Merging for Seamless Continual Learning. ECCV (85) Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert
2024	J	`jnl`	MagMax: Leveraging Model Merging for Seamless Continual Learning. CoRR Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert
2024	A	`conf`	Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning. WACV Alex Gomez-Villa, Bartlomiej Twardowski, Kai Wang, Joost van de Weijer
2024	J	`jnl`	Realistic Evaluation of Test-Time Adaptation Algorithms: Unsupervised Hyperparameter Selection. CoRR Sebastian Cygert, Damian Sójka, Tomasz Trzcinski, Bartlomiej Twardowski
2024	A*	`conf`	Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning. CVPR Dipam Goswami, Albin Soutif-Cormerais, Yuyang Liu, Sandesh Kamath, Bartlomiej Twardowski, Joost van de Weijer
2024	J	`jnl`	Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning. CoRR Dipam Goswami, Albin Soutif-Cormerais, Yuyang Liu, Sandesh Kamath, Bartlomiej Twardowski, Joost van de Weijer
2024	—	`conf`	Revisiting Supervision for Continual Representation Learning. ECCV (6) Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2024	A*	`conf`	Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning. NeurIPS Grzegorz Rypesc, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2024	J	`jnl`	Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning. CoRR Grzegorz Rypesc, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2024	J	`jnl`	The Art of Deception: Color Visual Illusions and Diffusion Models. CoRR Alex Gomez-Villa, Kai Wang, C. Alejandro Párraga, Bartlomiej Twardowski, Jesus Malo, Javier Vazquez-Corral, Joost van de Weijer
2024	A	`conf`	Zero-Waste Machine Learning. ECAI Tomasz Trzcinski, Bartlomiej Twardowski, Bartosz Zielinski, Kamil Adamczewski, Bartosz Wójcik
2023	—	`conf`	AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation. ICCV (Workshops) Damian Sójka, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
2023	J	`jnl`	AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation. CoRR Damian Sójka, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
2023	—	`conf`	Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning. ICCV (Workshops) Filip Szatkowski, Mateusz Pyla, Marcin Przewiezlikowski, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
2023	J	`jnl`	Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning. CoRR Filip Szatkowski, Mateusz Pyla, Marcin Przewiezlikowski, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
2023	J	`jnl`	Augmentation-aware Self-supervised Learning with Guided Projector. CoRR Marcin Przewiezlikowski, Mateusz Pyla, Bartosz Zielinski, Bartlomiej Twardowski, Jacek Tabor, Marek Smieja
2023	J	`jnl`	Bayesian Flow Networks in Continual Learning. CoRR Mateusz Pyla, Kamil Deja, Bartlomiej Twardowski, Tomasz Trzcinski
2023	J	`jnl`	Class-Incremental Learning: Survey and Performance Evaluation on Image Classification. IEEE Trans. Pattern Anal. Mach. Intell. Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, Joost van de Weijer
2023	J	`jnl`	Exploiting Graph Structured Cross-Domain Representation for Multi-Domain Recommendation. CoRR Alejandro Ariza-Casabona, Bartlomiej Twardowski, Tri Kurniawan Wijaya
2023	—	`conf`	Exploiting Graph Structured Cross-Domain Representation for Multi-domain Recommendation. ECIR (1) Alejandro Ariza-Casabona, Bartlomiej Twardowski, Tri Kurniawan Wijaya
2023	A*	`conf`	FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning. NeurIPS Dipam Goswami, Yuyang Liu, Bartlomiej Twardowski, Joost van de Weijer
2023	J	`jnl`	FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning. CoRR Dipam Goswami, Yuyang Liu, Bartlomiej Twardowski, Joost van de Weijer
2023	J	`jnl`	FedFNN: Faster Training Convergence Through Update Predictions in Federated Recommender Systems. CoRR Francesco Fabbri, Xianghang Liu, Jack R. McKenzie, Bartlomiej Twardowski, Tri Kurniawan Wijaya
2023	J	`jnl`	Generalized Continual Category Discovery. CoRR Daniel Marczak, Grzegorz Rypesc, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2023	A*	`conf`	ICICLE: Interpretable Class Incremental Continual Learning. ICCV Dawid Rymarczyk, Joost van de Weijer, Bartosz Zielinski, Bartlomiej Twardowski
2023	J	`jnl`	ICICLE: Interpretable Class Incremental Continual Learning. CoRR Dawid Rymarczyk, Joost van de Weijer, Bartosz Zielinski, Bartlomiej Twardowski
2023	—	`conf`	Looking through the past: better knowledge retention for generative replay in continual learning. ICCV (Workshops) Valeriya Khan, Sebastian Cygert, Bartlomiej Twardowski, Tomasz Trzcinski
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`	MM-GEF: Multi-modal representation meet collaborative filtering. CoRR Hao Wu, Alejandro Ariza-Casabona, Bartlomiej Twardowski, Tri Kurniawan Wijaya
2023	A*	`conf`	Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training. ICLR Simone Zini, Alex Gomez-Villa, Marco Buzzelli, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2023	J	`jnl`	Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning. CoRR Alex Gomez-Villa, Bartlomiej Twardowski, Kai Wang, Joost van de Weijer
2023	J	`jnl`	Revisiting Supervision for Continual Representation Learning. CoRR Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, Bartlomiej Twardowski
2023	J	`jnl`	Technical Report for ICCV 2023 Visual Continual Learning Challenge: Continuous Test-time Adaptation for Semantic Segmentation. CoRR Damian Sójka, Yuyang Liu, Dipam Goswami, Sebastian Cygert, Bartlomiej Twardowski, Joost van de Weijer
2022	—	`conf`	Continually Learning Self-Supervised Representations with Projected Functional Regularization. CVPR Workshops Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, Joost van de Weijer
2022	J	`jnl`	Online Meta-Learning for Model Update Aggregation in Federated Learning for Click-Through Rate Prediction. CoRR Xianghang Liu, Bartlomiej Twardowski, Tri Kurniawan Wijaya
2022	J	`jnl`	Planckian jitter: enhancing the color quality of self-supervised visual representations. CoRR Simone Zini, Marco Buzzelli, Bartlomiej Twardowski, Joost van de Weijer
2021	J	`jnl`	Continually Learning Self-Supervised Representations with Projected Functional Regularization. CoRR Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, Joost van de Weijer
2021	—	`conf`	Metric Learning for Session-Based Recommendations. ECIR (1) Bartlomiej Twardowski, Pawel Zawistowski, Szymon Zaborowski
2021	J	`jnl`	Metric Learning for Session-based Recommendations. CoRR Bartlomiej Twardowski, Pawel Zawistowski, Szymon Zaborowski
2021	J	`jnl`	On the importance of cross-task features for class-incremental learning. CoRR Albin Soutif-Cormerais, Marc Masana, Joost van de Weijer, Bartlomiej Twardowski
2021	—	`conf`	Reducing Label Effort: Self-Supervised meets Active Learning. ICCVW Javad Zolfaghari Bengar, Joost van de Weijer, Bartlomiej Twardowski, Bogdan Raducanu
2021	J	`jnl`	Reducing Label Effort: Self-Supervised meets Active Learning. CoRR Javad Zolfaghari Bengar, Joost van de Weijer, Bartlomiej Twardowski, Bogdan Raducanu
2020	J	`jnl`	Class-incremental learning: survey and performance evaluation. CoRR Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, Joost van de Weijer
2020	J	`jnl`	On Class Orderings for Incremental Learning. CoRR Marc Masana, Bartlomiej Twardowski, Joost van de Weijer
2020	A*	`conf`	Orderless Recurrent Models for Multi-Label Classification. CVPR Vacit Oguz Yazici, Abel Gonzalez-Garcia, Arnau Ramisa, Bartlomiej Twardowski, Joost van de Weijer
2020	A*	`conf`	RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning. NeurIPS Riccardo Del Chiaro, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2020	J	`jnl`	RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning. CoRR Riccardo Del Chiaro, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2020	A*	`conf`	Semantic Drift Compensation for Class-Incremental Learning. CVPR Lu Yu, Bartlomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, Joost van de Weijer
2020	J	`jnl`	Semantic Drift Compensation for Class-Incremental Learning. CoRR Lu Yu, Bartlomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, Joost van de Weijer
2019	J	`jnl`	Deep Learning Optimization Tasks and Metaheuristic Methods. Fundam. Informaticae Rafal Biedrzycki, Pawel Zawistowski, Bartlomiej Twardowski
2019	J	`jnl`	Orderless Recurrent Models for Multi-label Classification. CoRR Vacit Oguz Yazici, Abel Gonzalez-Garcia, Arnau Ramisa, Bartlomiej Twardowski, Joost van de Weijer
2016	A	`conf`	Modelling Contextual Information in Session-Aware Recommender Systems with Neural Networks. RecSys Bartlomiej Twardowski
2015	—	`conf`	IoT and Context-Aware Mobile Recommendations Using Multi-agent Systems. WI-IAT (1) Bartlomiej Twardowski, Dominik Ryzko
2014	—	`conf`	Multi-agent Architecture for Real-Time Big Data Processing. WI-IAT (3) Bartlomiej Twardowski, Dominik Ryzko
2012	Misc	`conf`	Domain Dependent Product Feature and Opinion Extraction Based on E-Commerce Websites. MISSI Bartlomiej Twardowski, Piotr Gawrysiak

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.