PGPaweł Gora

Paweł Gora

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Paweł Gora has a total of 58 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • QuantumGS: Quantum Encoding Framework for Gaussian Splatting

    by Grzegorz Wilczyński, Rafał Tobiasz, Paweł Gora, Marcin Mazur, Przemysław Spurek

  • Open Access

    Graph Coarsening Approach to the Vehicle Routing Problem: An Approximation Strategy

    by Katarzyna Nałęcz-Charkiewicz, Arnav Das, Turbasu Chatterjee, Joshua Keene, Paweł Gora, Carlos C. N. Kuhn

    In the Noisy Intermediate-Scale Quantum (NISQ) era of quantum computing, solving complex optimization problems such as the Vehicle Routing Problem (VRP) remains a formidable challenge. To overcome this obstacle, we introduce a novel method in this paper that focuses on reducing the number of edges in a graph based on Euclidean distances between vertices while preserving the crucial characteristics needed for solving the VRP. Our graph coarsening approach combined with the inflation method enables the reduced graph to be processed efficiently by classical, quantum or hybrid (quantum-classical) solvers, resulting in a faster computation time. When using the proposed method with hybrid algorithms, we have demonstrated an improvement of approximately 50% in the solution found by the hybrid solver. The practicality of our method on quantum hardware highlights its potential to contribute to the advancement of quantum and hybrid algorithms and applications during the NISQ era.


  • Graph-Based Sparse Neural Networks for Traffic Signal Optimization

    by Łukasz Skowronek, Paweł Gora, Marcin Możejko, Arkadiusz Klemenko


  • Open Access

    Identifying Promising Candidate Radiotherapy Protocols via GPU-GA in-silico

    by Wojciech Ozimek, Rafał Banaś, Paweł Gora, Simon D. Angus, Monika J. Piotrowska

    Around half of all cancer patients, world-wide, will receive some form of radiotherapy (RT) as part of their treatment. And yet, despite the rapid advance of high-throughput screening to identify successful chemotherapy drug candidates, there is no current analogue for RT protocol screening or discovery at any scale. Here we introduce and demonstrate the application of a high-throughput/high-fidelity coupled tumour-irradiation simulation approach, we call "GPU-GA", and apply it to human breast cancer analogue - EMT6/Ro spheroids. By analysing over 9.5 million candidate protocols, GPU-GA yields significant gains in tumour suppression versus prior state-of-the-art high-fidelity/-low-throughput computational search under two clinically relevant benchmarks. By extending the search space to hypofractionated areas (> 2 Gy/day) yet within total dose limits, further tumour suppression of up to 33.7% compared to state-of-the-art is obtained. GPU-GA could be applied to any cell line with sufficient empirical data, and to many clinically relevant RT considerations.

  • Top Cited Papers
    Open Access

    Quantum games and interactive tools for quantum technologies outreach and education

    by Zeki C. Seskir, Piotr Migdał, Carrie Weidner, Aditya Anupam, Nicky Case, Noah Davis, Chiara Decaroli, İlke Ercan, Caterina Foti, Paweł Gora, et al.

    The second quantum revolution1 has been unfolding for over two decades, and numerous countries across the globe acknowledge the potential of these technologies. In the last decade, more than 15 publicly supported national initiatives were launched, with several of them having budgets exceeding billion euros, particularly in the UK,2 the US,3 the EU,4 France,5 Germany,6 India,7 and China.8 Both the number of new publications per year9 and the number of patents10 granted on quantum technologies (QT) have been climbing steadily for the last decade, along with the growing number of start-ups and renowned companies getting into the field. Recently, the field has been receiving attention from private funding sources, which some have been referring to as the ‘quantum gold rush.’11 Within two decades, QT has advanced from a topic that was mainly discussed in physics conferences to becoming a strong contender for a potential future industry.


  • Using Cellular Automata to Compare SARS-CoV-2 Infectiousness in Different POIs and Under Different Conditions

    by Agnieszka Motyka, Aleksandra Bartnik, Aleksandra Żurko, Marta Giziewska, Paweł Gora, Jacek Sroka

  • Open Access

    Predicting times of waiting on red signals using BERT

    by Witold Szejgis, Anna Warno, Paweł Gora

    We present a method for approximating outcomes of road traffic simulations using BERT-based models, which may find applications in, e.g., optimizing traffic signal settings, especially with the presence of autonomous and connected vehicles. The experiments were conducted on a dataset generated using the Traffic Simulation Framework software runs on a realistic road network. The BERT-based models were compared with 4 other types of machine learning models (LightGBM, fully connected neural networks and 2 types of graph neural networks) and gave the best results in terms of all the considered metrics.

  • New Hybrid Quantum Annealing Algorithms for Solving Vehicle Routing Problem

    by Michał Borowski, Paweł Gora, Katarzyna Karnas, Mateusz Błajda, Krystian Król, Artur Matyjasek, Damian Burczyk, Miron Szewczyk, Michał Kutwin

    We introduce new hybrid algorithms, DBSCAN Solver and Solution Partitioning Solver, which use quantum annealing for solving Vehicle Routing Problem (VRP) and its practical variant: Capacitated Vehicle Routing Problem (CVRP). Both algorithms contain important classical components, but we also present two other algorithms, Full QUBO Solver and Average Partitioning Solver, which can be run only on a quantum processing unit (without CPU) and were prototypes which helped us develop better hybrid approaches. In order to validate our methods, we run comprehensive tests using D-Wave’s Leap framework on well-established benchmark test cases as well as on our own test scenarios built based on realistic road networks. We also compared our new quantum and hybrid methods with classical algorithms - well-known metaheuristics for solving VRP and CVRP. The experiments indicate that our hybrid methods give promising results and are able to find solutions of similar or even better quality than the tested classical algorithms.


  • Open Access

    Investigating performance of neural networks and gradient boosting models approximating microscopic traffic simulations in traffic optimization tasks

    by Paweł Gora, Maciej Brzeski, Marcin Możejko, Arkadiusz Klemenko, Adrian Kochański

    We analyze the accuracy of traffic simulations metamodels based on neural networks and gradient boosting models (LightGBM), applied to traffic optimization as fitness functions of genetic algorithms. Our metamodels approximate outcomes of traffic simulations (the total time of waiting on a red signal) taking as an input different traffic signal settings, in order to efficiently find (sub)optimal settings. Their accuracy was proven to be very good on randomly selected test sets, but it turned out that the accuracy may drop in case of settings expected (according to genetic algorithms) to be close to local optima, which makes the traffic optimization process more difficult. In this work, we investigate 16 different metamodels and 20 settings of genetic algorithms, in order to understand what are the reasons of this phenomenon, what is its scale, how it can be mitigated and what can be potentially done to design better real-time traffic optimization methods.