Adam Żychowski

Data augmentation (DA) has become one of the most effective strategies for obtaining large training datasets, enhancing model efficiency, improving generalization, and reducing biases caused by incomplete data. It is particularly important in computer vision (CV), where vast amounts of data are required and where most state-of-the-art approaches are based on deep learning. In this work, we present a comprehensive review of augmentation techniques in CV, including various transformations (perturbing existing data) and synthesis (generating new samples). We propose a well-structured taxonomy that covers both traditional methods and emerging trends. In terms of temporal scope, we aim to cover the most important DA methods for CV, from early applications in 1990 up to the year 2025. CV is a broad field, however, nearly all of the reviewed papers focus on image or video processing. We discuss multi-domain techniques as well as those designed for contextspecific modalities and applications, e.g., medical, underwater, or infrared imaging. Current and future challenges are addressed, and we also review available programming tools for practitioners.

This paper proposes the Augmented Decision Space Optimization (ADSO) framework for sparsity-driven optimization of mixed strategies in Stackelberg Security Games (SSGs). Unlike conventional evolutionary search processes that gradually converge toward sparse solutions, ADSO integrates binary variables to explicitly encode the inclusion or exclusion of pure strategies, while real-valued variables fine-tune their selection probabilities. This dual representation directly enforces sparsity and facilitates computational efficiency in large-scale problem instances. Extensive empirical studies on three benchmark games demonstrate that ADSO consistently produces compact strategies with minimal computational cost, achieving performance comparable to exact methods where they are feasible, and delivering state-of-the-art results in settings beyond the reach of such methods. Apart from SSGs, the framework exhibits strong potential for broader application to other game-theoretic and combinatorial optimization problems characterized by sparse solutions.

This paper examines the reasoning capabilities of Large Language Models (LLMs) from a novel perspective, focusing on their ability to operate within formally specified, rule-governed environments. We evaluate four LLMs (Gemini 2.5 Pro and Flash variants, Llama 3.3 70B and GPT-OSS 120B) on a suite of forward-simulation tasks-including next / multistep state formulation, and legal action generation-across a diverse set of reasoning problems illustrated through General Game Playing (GGP) game instances. Beyond reporting instance-level performance, we characterize games based on 40 structural features and analyze correlations between these features and LLM performance. Furthermore, we investigate the effects of various game obfuscations to assess the role of linguistic semantics in game definitions and the impact of potential prior exposure of LLMs to specific games during training. The main results indicate that three of the evaluated models generally perform well across most experimental settings, with performance degradation observed as the evaluation horizon increases (i.e., with a higher number of game steps). Detailed case-based analysis of the LLM performance provides novel insights into common reasoning errors in the considered logic-based problem formulation, including hallucinated rules, redundant state facts, or syntactic errors. Overall, the paper reports clear progress in formal reasoning capabilities of contemporary models.