Podróż przez ewolucję współpracy ludzi z AI, od pierwszych kroków do obecnych wyzwań. Jak będzie wyglądać ta relacja w przyszłości? Współpraca, rywalizacja, a może nowa symbioza?
This article presents the project's results, focused on the simulation of civilizations that develop over time. The development is primarily influenced by three main factors: the terrain on which the tribes are initially placed, available resources, and economic aspects, such as trading with one another. The world is generated using procedural techniques, which return a world with realistic...
The interpretability of artificial neural networks (ANNs) remains a challenge, particularly as they grow deeper and incorporate millions of parameters. Kolmogorov-Arnold Networks (KANs) address this issue by using fewer parameters than traditional ANNs and representing functions as symbolic formulas, while maintaining comparable performance.
John Conway's Game of Life (GoL) serves as an...
State-space models (SSMs) have emerged as a compelling
alternative to Transformer architectures, delivering comparable
performance at significantly lower computational cost. Al-
though deterministic SSMs such as Mamba have achieved
state-of-the-art results in areas like sequence modelling and
image segmentation, their deterministic nature limits their
suitability for probabilistic...
Line Follower Algorithm for a Flying Quadcopter
Mikołaj Stasiak, Wiktor Ważny, Grzegorz Zając
Institute for Automation and Robotics, Faculty of Mechatronics, Warsaw University of Technology.
As interest in aerial drones and autonomous systems grows, so does the need for optimal solutions that can be run on minimalistic hardware. This paper describes an autonomous, vision-based...
With the increasing number of cyber threats, malware detection has become a critical challenge in cybersecurity. Traditional detection techniques, based on behavioral analysis and signature creation, present significant challenges due to their time-consuming nature and limited effectiveness against new, unknown threats. This paper explores the optimization of artificial intelligence (AI) for...
I. BACKGROUND
Pulmonary Embolism (PE) is reported to be one of the most
common cardiovascular diseases. It is caused by a blood clot
that develops in a blood vessel elsewhere in the body and
travels to an artery in the lung, forming a blockage [1].
Lung V/Q (ventilation/perfusion) SPECT is one of an es-
tablished diagnostic imaging test for suspected PE. The idea
behind this test is...
Recent advances in deep learning and natural language processing have spurred the demand for deploying increasingly complex models on resource-constrained platforms. Modern browser environments, empowered by emerging GPU standards like WebGPU, now offer a promising venue for real-time AI inference. This paper provides an overview of leveraging WebGPU for accelerating inference directly within...
Missing values are a common phenomenon in real-world time series datasets and can significantly impact the precision and reliability of data analysis and machine learning models. This research project aims to discuss the types of missing data occurrence and test and analyze different possibilities of their imputation. The methods taken into consideration will start from the simplest ones based...
Japanese manga has captivated readers worldwide with its vibrant and expressive form of art that provides compelling storytelling with intricate visuals. However, for many fans outside of Japan, language barriers often stand in the way of fully experiencing the depth of these stories. Traditional translation from language to language, while effective, can be a very time-consuming and...
This paper investigates short-term energy produc-
tion forecasting in Poland using three distinct predictive mod-
els: LightGBM, an ARIMA-based model, and a Long Short-
Term Memory (LSTM) network. Leveraging historical data
from Poland’s energy sector, our study evaluates each model’s
performance in terms of accuracy, robustness, and computational
efficiency. The LightGBM model employs...
Large Language Models have gained widespread
recognition since OpenAI released their revolutionary model,
ChatGPT 3.5. Since then, many new approaches have emerged
to improve the capabilities and accuracy of these models for
different tasks. One such method involves using multi-agent
conversations. This article compares two multi-agent setups
designed to solve the Polish standardized...
Automated medical report generation from chest X-ray images is a critical area of research in medical AI, aiming to enhance diagnostic accuracy, reduce radiologists' workload, and improve patient care. The process involves analyzing medical images and translating visual findings into structured, clinically relevant textual reports. Traditional methods rely on human expertise, which is...
This article investigates the role of Retrieval-Augmented Generation (RAG) in enhancing Large Language Models (LLMs) with information about movies and TV series released beyond their training data. In this study, the Llama 3.2 3B LLM is leveraged and integrated with external movie-related data retrieved from the OMDb API to provide specific information about over 14000 titles released in 2024,...
With the increasing popularity of web services and the significant amount of time users spend online, cybercriminals are increasingly targeting this space with sophisticated malicious techniques. Phishing, one of the most prevalent cybersecurity threats, poses a substantial risk to both individuals and organizations. These attacks are typically executed via deceptive emails containing...
Short-term forecasting of cryptocurrency prices remains a challenging task due to the high volatility and complex market dynamics of digital assets like Ethereum. This study proposes a hybrid deep learning model, that integrates networks such as Bi-LSTM, FinBERT and GRU, seeking to provide a comprehensive analysis of their applicability in this domain and enhance predictive accuracy for this...
The paper aims to evaluate the effectiveness of available detectors in distinguishing fake from real photos. Deepfakes are artificially generated images or videos created using artificial intelligence or manual tools like Photoshop. New techniques, such as Generative Adversarial Networks (GANs) and Diffusion Models (DMs) enable the rapid generation of highly realistic images. The research...
Modern organizations generate vast amounts of data, a significant portion of which consists of system, network, and application logs. The sheer volume and scalability of these logs make manual analysis inefficient and highly time-consuming. Automated anomaly detection techniques have been developed and refined to accelerate this process. Currently it is common for open SIEM systems to only...
This paper investigates the utility of Principal Component Analysis (PCA) for multi-label classification of multispectral images using ResNet50 and DINOv2, acknowledging the high dimensionality of such data and the associated processing challenges. Multi-label classification, where each image may belong to multiple classes, adds further complexity to feature extraction. Our pipeline includes...
Understanding and interpreting the decisions made by deep learning models has become an essential area of research in artificial intelligence. Convolutional neural networks (CNNs), despite their high performance in various tasks, often function as "black boxes," making it challenging to explain their predictions. This study focuses on applying and evaluating different explainability techniques...
Large language models (LLMs) are trained with ever-increasing amounts of data. It seems that when asked to solve mathematical tasks, they can infer and reason mathematically [1]. The GSM8K benchmark platform is widely used to test various LLMs to solve simple arithmetic tasks. Recently, LLMs have shown a clear improvement in their ability to correctly answer questions from the GSM8K dataset....
Franky: An Intelligent Agent for Stock Portfolio
Management Using Large Language Models and
Deep Reinforcement Learning
1st Mikołaj Zawada∗
Faculty of Electrical Engineering
Warsaw University of Technology
Warsaw, Poland
mikolaj.zawada.stud@pw.edu.pl
2nd Mateusz Bartosik∗
Faculty of Electrical Engineering
Warsaw University of Technology
Warsaw,...
This paper presents a hybrid framework combining Deep Neural Networks (DNNs) and Modern Portfolio Theory (MPT) to optimize football betting strategies. Leveraging historical match data from five major European leagues (2014–2025), we engineer predictive features such as dynamic Elo rankings, expected goals (xG), and team performance metrics derived from raw game statistics. Diverse neural...
This paper presents a comprehensive approach to the evaluation of physical exercise using skeletal estimation and motion analysis. The research begins with the acquisition of relevant datasets and a review of existing monocular pose estimation solutions. A key component of this work is modeling important features, including skeletal joint weighting and key angles between them, according to...
The rise of quantum computing presents a significant threat to classical cryptographic systems, particularly those relying on hard mathematical problems such as integer factorization and discrete logarithms. This paper explores the impact of quantum computing on traditional cryptographic algorithms and the necessity of transitioning to quantum-resistant cryptography. We provide an overview of...
This paper presents a comprehensive comparison of several state-of-the-art proxy loss methods for retail product recognition, focusing on accuracy, computational efficiency, embedding quality, and convergence behaviour. An extensive evaluation is performed on the Stanford Online Products benchmark dataset, which contains over 120,000 images covering 22,634 distinct product categories. The...
Sygnał elektroencefalograficzny (EEG) może ulegać zakłóceniom spowodowanym przez aktywność elektryczną niezwiązaną bezpośrednio z pracą mózgu badanego. Zjawisko to określane jest jako problem artefaktów EEG, które dzielimy na techniczne i fizjologiczne. Do artefaktów fizjologicznych należą charakterystyczne fragmenty sygnału rejestrowane w wyniku ruchów gałek ocznych, mrugania, czy aktywności...
This comprehensive survey examines consensus al-
gorithms utilized in Distributed Ledger Technology (DLT) for
Internet of Things (IoT) environments. The paper provides a
comparative analysis of consensus protocols including Proof of
Work, Proof of Stake, Proof of Authority, Proof of Elapsed Time,
Proof of Space, Proof of Activity, Practical Byzantine Fault Tol-
erance algorithm and...
Recurrent Neural Networks (RNN) and their other variants such as Long-Short Term Memory (LSTM) networks have become a widely used tool for natural langague processing (NLP). Thanks to their ability to effectively capture sequential dependencies in textual data they are well-suited for determining sentiment expressed in user-generated data such as media posts or reviews. However despite their...
W artykule przedstawione zostały dotychczasowe postępy projektu Badania i Implementacja Innowacyjnego Systemu Zasobnika Energii Współpracującego z Odnawialnymi Źródłami Energii INNOSTOR dla Zrównoważonego Rozwoju na Politechnice Warszawskiej realizowanego przez koło naukowe IskIErka w ramach grantu rektorskiego. Opisany został ogólny kierunek zmian w elektroenergetyce, dążący do coraz...
This paper presents a comparative study of different neural network architectures trained using behavioral learning in the strategic board game Blood Bowl. The game’s complexity, driven by its large branching factor and inherent randomness, presents a significant challenge for artificial intelligence (AI). Traditional AI approaches, such as scripted and search-based methods, have struggled to...
The choice of a frontend framework significantly impacts the performance, maintainability, and scalability of modern web applications. This paper presents a comparative analysis of Blazor and React, two popular frontend frameworks with distinct architectures and approaches to building web interfaces. Blazor, developed by Microsoft, leverages C# and .NET to enable web development using...
This paper compares technologies used to develop mobile applications using multiplatform technologies. A lack of analysis of newer technologies, such as Kotlin Multiplatform, was identified by researching the current state of this field. Therefore, this study aims to compare the Kotlin Multiplatform with existing and well-researched Flutter technology to advance mobile development techniques....
\documentclass[conference]{IEEEtran}
\usepackage[T1]{fontenc}
\usepackage{lscape}
\IEEEoverridecommandlockouts
% The preceding line is only needed to identify funding in the first footnote. If that is unneeded, please comment it...
Study on how in the multitenant cloud architecture of the Salesforce platform, different field configurations available to administrators impact database index usage, query costs, and data manipulation language operations. Results show that while "External ID" and "Unique" settings consistently create indexes with varying performance effects, the "Required" flag unexpectedly affects query...
This study focuses on optimizing the computational efficiency of simulating electric field distribution in the human brain using the finite element method (FEM). Due to the brain’s complex and heterogeneous structure, accurate modeling requires high-resolution segmentation and realistic electrical property assignments, leading to large-scale numerical problems. To address these challenges,...
Humans can perceive a much broader luminance range than an average camera. It is impossible to take a single photo that contains details for both very dark and bright areas.
HDRI (High Dynamic Range Imaging) methods address that problem, by merging multiple low dynamic range images (LDR) into a single picture. These methods are being used for professional cameras and even in smartphones.
The...
This presentation explores the development of a low-cost, home-built quantum computer aimed at validating hypotheses from numerical simulations, combining theoretical advancements in quantum computing with practical engineering solutions. Three configurations are discussed: an Intel Labs-inspired setup demonstrating pulse-level control programming with PennyLane and benchmarking using the...
This paper explores the relationship between carbon reduction efforts, ESG factors and financial performance. Machine learning models are applied to multi-industry data to assess whether carbon-related ESG attributes - such as carbon emissions and participation in emissions trading schemes - enhance the prediction of stock returns. The analysis also considers the concept of a carbon premium,...
Abstract—In modern software systems, efficient communication
is essential for ensuring scalability, maintainability, and performance.
The aim of this article is to review key communication
mechanisms used in modern systems. A multi-stage selection
process was conducted to identify the most relevant scientific
articles, summarize research findings, and determine which
methods perform best...
JavaScript remains the dominant language for
client-side scripting, while WebAssembly offers near-native ex
ecution speeds, making it a compelling choice for computa
tionally intensive tasks. This study provides a comprehensive
analysis of the performance differences between WebAssembly
and JavaScript across various computing environments, includ
ing different browsers (Firefox,...
Wersja polska
Celem pracy jest przedstawienie robota modularnego Gizmo - jego budowy mechanicznej, koncepcji rozproszonego układu sterowania oraz protokołu komunikacji międzymodułowej. Zawiera ona również omówienie fizycznego modelu wykonanego z użyciem druku 3D. Każdy z segmentów posiada niezależne aktuatory oraz zdolność do łączenia się i rekonfiguracji. Cechy te sprawią, że roboty...
Dynamiczny rozwój sztucznej inteligencji oraz mediów społecznościowych zwiększają potrzebę skutecznej ochrony przekazywanych danych. Znakowanie wodne jest jedną z możliwych technik modyfikujących m. in. obrazy w celu śledzenia przepływu informacji i pochodzenia. W niniejszej pracy przeanalizowano różne techniki znakowania wodnego, obejmujące zarówno tradycyjne algorytmy, jak i nowoczesne...
This paper discusses the implementation of the particle-mesh (PM) and particle-particle particle-mesh (P3M) methods in the context of a spiral galaxy simulation. Simulations performed using both methods correctly predict the formation of characteristic spiral arms and demonstrate expected physical behavior, satisfying Newton’s second law and conserving energy and angular momentum. The PM code...
Enabling robots to operate autonomously in dynamic environments over extended periods requires robust memory, reasoning, and decision-making capabilities. Although large language models (LLMs) have demonstrated significant potential, their limited context size constrains their ability to manage long-term data effectively. Autonomous systems must be able to provide detailed information about a...
The rapid expansion of Industrial Internet of Things (IoT) networks has increased security vulnerabilities, necessitating robust threat detection mechanisms. Industrial networks may hold non-critical data and confidential energy or medical data. The second group should therefore be covered by stringent security policies against Denial of Service attacks or attempts to steal information through...
Efektywna komunikacja między zespołami IT a biznesem jest jednym z kluczowych czynników sukcesu projektów. Jednak różnice w oczekiwaniach, niejasne wymagania oraz nieskuteczne spotkania często prowadzą do barier we współpracy. Niniejsza praca identyfikuje najistotniejsze wyzwania komunikacyjne oraz analizuje wpływ technik facylitacyjnych na usprawnienie współpracy w projektach IT, koncentrując...
Zmiany w oprogramowaniu stanowią największą część kosztów ponoszonych podczas jego utrzymywania. Optymalizacja kosztów, a w szczególności czasu poświęconego na wprowadzanie zmian umożliwia organizacjom utrzymującym oprogramowanie uzyskanie przewagi konkurencyjnej. Kluczową aktywnością w modyfikacji kodu źródłowego jest jego zrozumienie, na co wpływ ma zastosowana struktura klas.
Prezentacja...
