Mikołaj Małkiński
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mikołaj Małkiński has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Jacek Mańdziuk
Warsaw University of Technology
9 shared publications Jacek Mańdziuk
1 shared publication- Szymon Pawlonka
Warsaw University of Technology
1 shared publication
Latest Publications
- 1 November 2025
- Published by Springer Nature
- p. 167-178
The Role of Text and Vision Modalities in Solving Bongard Problems with VLMs
- 1 November 2025
- Published by Springer Nature
- p. 167-178
The Role of Text and Vision Modalities in Solving Bongard Problems with VLMs
- 4 October 2025
- Published by Springer Nature
- p. 112-129
A Unified View of Abstract Visual Reasoning Problems
- 4 October 2025
- Published by Springer Nature
- p. 112-129
A Unified View of Abstract Visual Reasoning Problems
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 7, 5932-5940
A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning
We study generalization and knowledge reuse capabilities of deep neural networks in the domain of abstract visual reasoning (AVR), employing Raven's Progressive Matrices (RPMs), a recognized benchmark task for assessing AVR abilities. Two knowledge transfer scenarios referring to the I-RAVEN dataset are investigated. Firstly, inspired by generalization assessment capabilities of the PGM dataset and popularity of I-RAVEN, we introduce Attributeless-I-RAVEN (A-I-RAVEN), a benchmark with 10 generalization regimes that allow to systematically test generalization of abstract rules applied to held-out attributes at various levels of complexity (primary and extended regimes). In contrast to PGM, A-I-RAVEN features compositionality, a variety of figure configurations, and does not require substantial computational resources. Secondly, we construct I-RAVEN-Mesh, a dataset that enriches RPMs with a novel component structure comprising line-based patterns, facilitating assessment of progressive knowledge acquisition in transfer learning setting. We evaluate 13 strong models from the AVR literature on the introduced datasets, revealing their specific shortcomings in generalization and knowledge transfer.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 7, 5932-5940
Open AccessA-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning
We study generalization and knowledge reuse capabilities of deep neural networks in the domain of abstract visual reasoning (AVR), employing Raven's Progressive Matrices (RPMs), a recognized benchmark task for assessing AVR abilities. Two knowledge transfer scenarios referring to the I-RAVEN dataset are investigated. Firstly, inspired by generalization assessment capabilities of the PGM dataset and popularity of I-RAVEN, we introduce Attributeless-I-RAVEN (A-I-RAVEN), a benchmark with 10 generalization regimes that allow to systematically test generalization of abstract rules applied to held-out attributes at various levels of complexity (primary and extended regimes). In contrast to PGM, A-I-RAVEN features compositionality, a variety of figure configurations, and does not require substantial computational resources. Secondly, we construct I-RAVEN-Mesh, a dataset that enriches RPMs with a novel component structure comprising line-based patterns, facilitating assessment of progressive knowledge acquisition in transfer learning setting. We evaluate 13 strong models from the AVR literature on the introduced datasets, revealing their specific shortcomings in generalization and knowledge transfer.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 7, 5941-5949
Advancing Generalization Across a Variety of Abstract Visual Reasoning Tasks
The abstract visual reasoning (AVR) domain presents a diverse suite of analogy-based tasks devoted to studying model generalization. Recent years have brought dynamic progress in the field, particularly in i.i.d. scenarios, in which models are trained and evaluated on the same data distributions. Nevertheless, o.o.d. setups that assess model generalization to new test distributions remain challenging even for the most recent models. To advance generalization in AVR tasks, we present the Pathways of Normalized Group Convolution model (PoNG), a novel neural architecture that features group convolution, normalization, and a parallel design. We consider a wide set of AVR benchmarks, including Raven's Progressive Matrices and visual analogy problems with both synthetic and real-world images. The experiments demonstrate strong generalization capabilities of the proposed model, which in several settings outperforms the existing literature methods.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 7, 5941-5949
Open AccessAdvancing Generalization Across a Variety of Abstract Visual Reasoning Tasks
The abstract visual reasoning (AVR) domain presents a diverse suite of analogy-based tasks devoted to studying model generalization. Recent years have brought dynamic progress in the field, particularly in i.i.d. scenarios, in which models are trained and evaluated on the same data distributions. Nevertheless, o.o.d. setups that assess model generalization to new test distributions remain challenging even for the most recent models. To advance generalization in AVR tasks, we present the Pathways of Normalized Group Convolution model (PoNG), a novel neural architecture that features group convolution, normalization, and a parallel design. We consider a wide set of AVR benchmarks, including Raven's Progressive Matrices and visual analogy problems with both synthetic and real-world images. The experiments demonstrate strong generalization capabilities of the proposed model, which in several settings outperforms the existing literature methods.
- Open Access
Advancing Generalization Across a Variety of Abstract Visual Reasoning Tasks
The abstract visual reasoning (AVR) domain presents a diverse suite of analogy-based tasks devoted to studying model generalization. Recent years have brought dynamic progress in the field, particularly in i.i.d. scenarios, in which models are trained and evaluated on the same data distributions. Nevertheless, o.o.d. setups that assess model generalization to new test distributions remain challenging even for the most recent models. To advance generalization in AVR tasks, we present the Pathways of Normalized Group Convolution model (PoNG), a novel neural architecture that features group convolution, normalization, and a parallel design. We consider a wide set of AVR benchmarks, including Raven's Progressive Matrices and visual analogy problems with both synthetic and real-world images. The experiments demonstrate strong generalization capabilities of the proposed model, which in several settings outperforms the existing literature methods.
Open AccessAdvancing Generalization Across a Variety of Abstract Visual Reasoning Tasks
The abstract visual reasoning (AVR) domain presents a diverse suite of analogy-based tasks devoted to studying model generalization. Recent years have brought dynamic progress in the field, particularly in i.i.d. scenarios, in which models are trained and evaluated on the same data distributions. Nevertheless, o.o.d. setups that assess model generalization to new test distributions remain challenging even for the most recent models. To advance generalization in AVR tasks, we present the Pathways of Normalized Group Convolution model (PoNG), a novel neural architecture that features group convolution, normalization, and a parallel design. We consider a wide set of AVR benchmarks, including Raven's Progressive Matrices and visual analogy problems with both synthetic and real-world images. The experiments demonstrate strong generalization capabilities of the proposed model, which in several settings outperforms the existing literature methods.
- Top Cited PapersOpen Access
- 21 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (7) , 1-36
Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
Visual reasoning (AVR) domain encompasses problems solving which requires the ability to reason about relations among entities present in a given scene. While humans, generally, solve AVR tasks in a “natural” way, even without prior experience, this type of problem has proven difficult for current machine learning systems. The paper summarises recent progress in applying deep learning methods to solving AVR problems, as a proxy for studying machine intelligence. We focus on the most common type of AVR tasks—the Raven’s Progressive Matrices (RPMs)—and provide a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as present the RPM benchmark sets. Performance analysis of the state-of-the-art approaches to solving RPMs leads to formulation of certain insights and remarks on the current and future trends in this area. We also attempt to put RPM studies in a more general perspective and demonstrate how real-world problems from the outside of AVR area can benefit from the presented research.
- 21 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (7) , 1-36
Top Cited PapersOpen AccessDeep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
Visual reasoning (AVR) domain encompasses problems solving which requires the ability to reason about relations among entities present in a given scene. While humans, generally, solve AVR tasks in a “natural” way, even without prior experience, this type of problem has proven difficult for current machine learning systems. The paper summarises recent progress in applying deep learning methods to solving AVR problems, as a proxy for studying machine intelligence. We focus on the most common type of AVR tasks—the Raven’s Progressive Matrices (RPMs)—and provide a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as present the RPM benchmark sets. Performance analysis of the state-of-the-art approaches to solving RPMs leads to formulation of certain insights and remarks on the current and future trends in this area. We also attempt to put RPM studies in a more general perspective and demonstrate how real-world problems from the outside of AVR area can benefit from the presented research.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (13) , 14297-14305
One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems
Visual Reasoning (AVR) comprises a wide selection of various problems similar to those used in human IQ tests. Recent years have brought dynamic progress in solving particular AVR tasks, however, in the contemporary literature AVR problems are largely dealt with in isolation, leading to highly specialized task-specific methods. With the aim of developing universal learning systems in the AVR domain, we propose the unified model for solving Single-Choice Abstract visual Reasoning tasks (SCAR), capable of solving various single-choice AVR tasks, without making any a priori assumptions about the task structure, in particular the number and location of panels. The proposed model relies on a novel Structure-Aware dynamic Layer (SAL), which adapts its weights to the structure of the considered AVR problem. Experiments conducted on Raven's Progressive Matrices, Visual Analogy Problems, and Odd One Out problems show that SCAR (SAL-based models, in general) effectively solves diverse AVR tasks, and its performance is on par with the state-of-the-art task-specific baselines. What is more, SCAR demonstrates effective knowledge reuse in multi-task and transfer learning settings. To our knowledge, this work is the first successful attempt to construct a general single-choice AVR solver relying on self-configurable architecture and unified solving method. With this work we aim to stimulate and foster progress on task-independent research paths in the AVR domain, with the long-term goal of development of a general AVR solver.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (13) , 14297-14305
Open AccessOne Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems
Visual Reasoning (AVR) comprises a wide selection of various problems similar to those used in human IQ tests. Recent years have brought dynamic progress in solving particular AVR tasks, however, in the contemporary literature AVR problems are largely dealt with in isolation, leading to highly specialized task-specific methods. With the aim of developing universal learning systems in the AVR domain, we propose the unified model for solving Single-Choice Abstract visual Reasoning tasks (SCAR), capable of solving various single-choice AVR tasks, without making any a priori assumptions about the task structure, in particular the number and location of panels. The proposed model relies on a novel Structure-Aware dynamic Layer (SAL), which adapts its weights to the structure of the considered AVR problem. Experiments conducted on Raven's Progressive Matrices, Visual Analogy Problems, and Odd One Out problems show that SCAR (SAL-based models, in general) effectively solves diverse AVR tasks, and its performance is on par with the state-of-the-art task-specific baselines. What is more, SCAR demonstrates effective knowledge reuse in multi-task and transfer learning settings. To our knowledge, this work is the first successful attempt to construct a general single-choice AVR solver relying on self-configurable architecture and unified solving method. With this work we aim to stimulate and foster progress on task-independent research paths in the AVR domain, with the long-term goal of development of a general AVR solver.
- Open Access
One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems
Abstract Visual Reasoning (AVR) comprises a wide selection of various problems similar to those used in human IQ tests. Recent years have brought dynamic progress in solving particular AVR tasks, however, in the contemporary literature AVR problems are largely dealt with in isolation, leading to highly specialized task-specific methods. With the aim of developing universal learning systems in the AVR domain, we propose the unified model for solving Single-Choice Abstract visual Reasoning tasks (SCAR), capable of solving various single-choice AVR tasks, without making any a priori assumptions about the task structure, in particular the number and location of panels. The proposed model relies on a novel Structure-Aware dynamic Layer (SAL), which adapts its weights to the structure of the considered AVR problem. Experiments conducted on Raven's Progressive Matrices, Visual Analogy Problems, and Odd One Out problems show that SCAR (SAL-based models, in general) effectively solves diverse AVR tasks, and its performance is on par with the state-of-the-art task-specific baselines. What is more, SCAR demonstrates effective knowledge reuse in multi-task and transfer learning settings. To our knowledge, this work is the first successful attempt to construct a general single-choice AVR solver relying on self-configurable architecture and unified solving method. With this work we aim to stimulate and foster progress on task-independent research paths in the AVR domain, with the long-term goal of development of a general AVR solver.
Open AccessOne Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems
Abstract Visual Reasoning (AVR) comprises a wide selection of various problems similar to those used in human IQ tests. Recent years have brought dynamic progress in solving particular AVR tasks, however, in the contemporary literature AVR problems are largely dealt with in isolation, leading to highly specialized task-specific methods. With the aim of developing universal learning systems in the AVR domain, we propose the unified model for solving Single-Choice Abstract visual Reasoning tasks (SCAR), capable of solving various single-choice AVR tasks, without making any a priori assumptions about the task structure, in particular the number and location of panels. The proposed model relies on a novel Structure-Aware dynamic Layer (SAL), which adapts its weights to the structure of the considered AVR problem. Experiments conducted on Raven's Progressive Matrices, Visual Analogy Problems, and Odd One Out problems show that SCAR (SAL-based models, in general) effectively solves diverse AVR tasks, and its performance is on par with the state-of-the-art task-specific baselines. What is more, SCAR demonstrates effective knowledge reuse in multi-task and transfer learning settings. To our knowledge, this work is the first successful attempt to construct a general single-choice AVR solver relying on self-configurable architecture and unified solving method. With this work we aim to stimulate and foster progress on task-independent research paths in the AVR domain, with the long-term goal of development of a general AVR solver.
- 11 November 2022
- Published by Elsevier in Information Fusion
- Vol. 91, 713-736
A review of emerging research directions in Abstract Visual Reasoning
- 11 November 2022
- Published by Elsevier in Information Fusion
- Vol. 91, 713-736
A review of emerging research directions in Abstract Visual Reasoning
- Open Access
- 6 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (2) , 1941-1953
Multi-Label Contrastive Learning for Abstract Visual Reasoning
For a long time, the ability to solve abstract reasoning tasks was considered one of the hallmarks of human intelligence. Recent advances in the application of deep learning (DL) methods led to surpassing human abstract reasoning performance, specifically in the most popular type of such problems—Raven’s progressive matrices (RPMs). While the efficacy of DL systems is indeed impressive, the way they approach the RPMs is very different from that of humans. State-of-the-art systems solving RPMs rely on massive pattern-based training and sometimes on exploiting biases in the dataset, whereas humans concentrate on the identification of the rules/concepts underlying the RPM to be solved. Motivated by this cognitive difference, this work aims at combining DL with the human way of solving RPMs. Specifically, we cast the problem of solving RPMs into a multilabel classification framework where each RPM is viewed as a multilabel data point, with labels determined by the set of abstract rules underlying the RPM. For efficient training of the system, we present a generalization of the noise contrastive estimation algorithm to the case of multilabel samples and a new sparse rule encoding scheme for RPMs. The proposed approach is evaluated on the two most popular benchmark datasets I-RAVEN and procedurally generated matrices (PGM) and on both of them demonstrate an advantage over the state-of-the-art results.
- 6 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (2) , 1941-1953
Open AccessMulti-Label Contrastive Learning for Abstract Visual Reasoning
For a long time, the ability to solve abstract reasoning tasks was considered one of the hallmarks of human intelligence. Recent advances in the application of deep learning (DL) methods led to surpassing human abstract reasoning performance, specifically in the most popular type of such problems—Raven’s progressive matrices (RPMs). While the efficacy of DL systems is indeed impressive, the way they approach the RPMs is very different from that of humans. State-of-the-art systems solving RPMs rely on massive pattern-based training and sometimes on exploiting biases in the dataset, whereas humans concentrate on the identification of the rules/concepts underlying the RPM to be solved. Motivated by this cognitive difference, this work aims at combining DL with the human way of solving RPMs. Specifically, we cast the problem of solving RPMs into a multilabel classification framework where each RPM is viewed as a multilabel data point, with labels determined by the set of abstract rules underlying the RPM. For efficient training of the system, we present a generalization of the noise contrastive estimation algorithm to the case of multilabel samples and a new sparse rule encoding scheme for RPMs. The proposed approach is evaluated on the two most popular benchmark datasets I-RAVEN and procedurally generated matrices (PGM) and on both of them demonstrate an advantage over the state-of-the-art results.