Abstract visual reasoning (AVR) involves discovering shared concepts across images through analogy, akin to solving IQ test problems. Bongard Problems (BPs) remain a key challenge in AVR, requiring both visual reasoning and verbal description. We investigate whether multimodal large language models (MLLMs) can solve BPs by formulating a set of diverse MLLM-suited solution strategies and testing $4$ proprietary and $4$ open-access models on $3$ BP datasets featuring synthetic (classic BPs) and real-world (Bongard HOI and Bongard-OpenWorld) images. Despite some successes on real-world datasets, MLLMs struggle with synthetic BPs. To explore this gap, we introduce Bongard-RWR, a dataset representing synthetic BP concepts using real-world images. Our findings suggest that weak MLLM performance on classical BPs is not due to the domain specificity, but rather comes from their general AVR limitations. Code and dataset are available at: https://github.com/pavonism/bongard-rwr

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.

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.

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.

Games have long served as an effective method for developing and testing artificial intelligence (AI) models designed to function in a complex and possibly adversarial environment. While computers have already outperformed humans in practically all traditional board games, such as checkers, chess or Go, as well as various games with imperfect information, e.g. Poker or Bridge, certain imperfect information games, especially those devised for the purpose of testing particular capabilities of AI agents, remain a challenge. An example of such a game is Reconnaissance Blind Chess (RBC) - a variant of chess in which players do not have full access to the information defining the current board state. In this paper, we present Zubat, an AI RBC playing agent. The agent harnesses the strength of the Stockfish chess engine and enriches it with auxiliary modules. Firstly, we propose to estimate the oppnnent's uncertainty with a recurrent neural network in order to prefer positions that maximize the opponent's uncertainty, thus impeding their selection of optimal moves. Secondly, we develop the risk-taker module that identifies high-reward moves that could potentially exploit the opponent's uncertainty. The mediator module is constructed to select a move to be played by combining all three pieces of available information (the Stockfish assessment of moves, the expected opponent's uncertainty level, potential gains from risk-taking moves). Experiments conducted in the publicly available RBC match-making system show high competitiveness of the proposed agent, which, at the time of writing, was ranked 2nd out of 117 bots and human players, on the RBC leaderboard.

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.