arXiv subjects

Paweł Gora

Publications and source records attributed to Paweł Gora.

10 recordsLinked to original sources

arXiv2026

GNN-Guided Graph Coarsening and Adaptive QUBO Penalties for the Capacitated Vehicle Routing Problem with Time Windows on a Quantum Annealer

Graph coarsening reduces the large Quadratic Unconstrained Binary Optimization (QUBO) formulations arising when vehicle-routing problems are solved by quantum annealing. Nearby customers with compatible time windows are merged into super-nodes, the reduced problem is solved, and the solution is expanded to the original graph. For the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW), existing coarsening heuristics require family-specific tuning and remain unreliable on random instances. We address these limitations on the Solomon benchmark using simulated annealing and a D-Wave Advantage2 processor. We first introduce adaptive penalty calibration. Uniform penalty scaling has little effect, whereas controlling the internal coefficient range substantially improves raw samples. Removing non-binding constraints, normalising binding ones, and scaling the remaining penalties reduces mean raw constraint violations from 33.0 to 0.06 at the same solver budget (p=3.7e-11, n=56). A variable-count-preserving control attributes this gain to conditioning rather than problem size. Second, we replace the hand-tuned merge score with a graph neural network (GNN) using one configuration across all families. At N=10, it achieves 100% feasibility across all Solomon families, including R-type (100% vs. 80% for the tuned heuristic). Across N=10,...,100, feasibility is 83% vs. 69%, with the GNN better or tied on 85/90 instance-size pairs. At N=80,100, the difference is significant (p=0.002; 25/25 pairs), while the QUBO remains approximately 5-6 times smaller. Finally, hardware experiments reproduce the conditioning effect at fixed logical variable count: feasible samples increase from 0.02% to 39% across 13 instances. Classical repair with local search remains a reference bound for end-to-end solution cost.

cs.LG↗

arXiv2026

A Payne-Whitham model of urban traffic networks in the presence of traffic lights and its application to traffic optimisation

Urban road transport is a major civilisational and economic challenge, affecting the quality of life and economic activity. Addressing these challenges requires a multidisciplinary approach and sustainable urban planning strategies to mitigate the negative effects of traffic in cities. In this paper, we introduce an extension of one of the most popular macroscopic traffic simulation models, the Payne-Whitham model. We investigate how this model, originally designed to model highway traffic on straight road segments, can be adapted to more realistic conditions with arbitrary road network graphs and multiple intersections with traffic signals. Furthermore, we showcase the practical application of this extension in experiments aimed at optimising traffic signal settings. For computational reasons, these experiments involve the adoption of surrogate models for approximating our extended Payne-Whitham model, and subsequently, we utilise the Differential Evolution optimization algorithm, resulting in the identification of traffic signal settings that enhance the average speed of cars and decrease the total length of queues, thereby facilitating smoother traffic flow.

math.AP↗

arXiv2026

QuantumGS: Quantum Encoding Framework for Gaussian Splatting

Recent advances in neural rendering, particularly 3D Gaussian Splatting (3DGS), have enabled real-time rendering of complex scenes. However, standard 3DGS relies on spherical harmonics, which often struggle to accurately capture high-frequency view-dependent effects such as sharp reflections and transparency. While hybrid approaches like Viewing Direction Gaussian Splatting (VDGS) mitigate this limitation using classical Multi-Layer Perceptrons (MLPs), they remain limited by the expressivity of classical networks in low-parameter regimes. In this paper, we introduce QuantumGS, a novel hybrid framework that integrates Variational Quantum Circuits (VQC) into the Gaussian Splatting pipeline. We propose a unique encoding strategy that maps the viewing direction directly onto the Bloch sphere, leveraging the natural geometry of qubits to represent 3D directional data. By replacing classical color-modulating networks with quantum circuits generated via a hypernetwork or conditioning mechanism, we achieve higher expressivity and better generalization. Source code is available in the supplementary material. Code is available at https://github.com/gwilczynski95/QuantumGS

quant-ph↗

arXiv2025

URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles

Connected Autonomous Vehicles (CAVs) promise to reduce congestion in future urban networks, potentially by optimizing their routing decisions. Unlike for human drivers, these decisions can be made with collective, data-driven policies, developed using machine learning algorithms. Reinforcement learning (RL) can facilitate the development of such collective routing strategies, yet standardized and realistic benchmarks are missing. To that end, we present URB: Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles. URB is a comprehensive benchmarking environment that unifies evaluation across 29 real-world traffic networks paired with realistic demand patterns. URB comes with a catalog of predefined tasks, multi-agent RL (MARL) algorithm implementations, three baseline methods, domain-specific performance metrics, and a modular configuration scheme. Our results show that, despite the lengthy and costly training, state-of-the-art MARL algorithms rarely outperformed humans. The experimental results reported in this paper initiate the first leaderboard for MARL in large-scale urban routing optimization. They reveal that current approaches struggle to scale, emphasizing the urgent need for advancements in this domain.

cs.LG↗

arXiv2025

POMO+: Leveraging starting nodes in POMO for solving Capacitated Vehicle Routing Problem

In recent years, reinforcement learning (RL) methods have emerged as a promising approach for solving combinatorial problems. Among RL-based models, POMO has demonstrated strong performance on a variety of tasks, including variants of the Vehicle Routing Problem (VRP). However, there is room for improvement for these tasks. In this work, we improved POMO, creating a method (\textbf{POMO+}) that leverages the initial nodes to find a solution in a more informed way. We ran experiments on our new model and observed that our solution converges faster and achieves better results. We validated our models on the CVRPLIB dataset and noticed improvements in problem instances with up to 100 customers. We hope that our research in this project can lead to further advancements in the field.

cs.AI↗

arXiv2023

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

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.

physics.med-ph↗

arXiv2022

Quantum Games and Interactive Tools for Quantum Technologies Outreach and Education

In this article, we provide an extensive overview of a wide range of quantum games and interactive tools that have been employed by the community in recent years. The paper presents selected tools, as described by their developers. The list includes Hello Quantum, Hello Qiskit, Particle in a Box, Psi and Delta, QPlayLearn, Virtual Lab by Quantum Flytrap, Quantum Odyssey, ScienceAtHome, and The Virtual Quantum Optics Laboratory. Additionally, we present events for quantum game development: hackathons, game jams, and semester projects. Furthermore, we discuss the Quantum Technologies Education for Everyone (QUTE4E) pilot project, which illustrates an effective integration of these interactive tools with quantum outreach and education activities. Finally, we aim at providing guidelines for incorporating quantum games and interactive tools in pedagogic materials to make quantum technologies more accessible for a wider population.

physics.ed-ph↗

arXiv2021

Predicting times of waiting on red signals using BERT

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.

cs.LG↗

arXiv2021

Modelling mobility and visualizing people's flow patterns in rural areas for future infrastructure development as a good transnational land-governance practice

This paper summarizes a cross-border mobility study, origin-destination mobility modelling and visualization, conducted in support of the infrastructure development efforts of local authorities and NGOs on the area over the Kayanga-Geba River, at the border between Senegal and Guinea Bissau. It builds on the data collected through participatory mapping for the elaboration of the Cross-Border Land Management and Development Plans (Plans PAGET) aiming to harmonize the different national territorial management tools into a unique transnational tool through the consideration of border areas as a territorial unity. Despite a small amount of available mobility data, we were able to build a mobility model for the considered area, and implemented it in the Traffic Simulation Framework, which was later used to calculate origin-destination matrices for the studied regions in two cases: with and without a cross-border mobility. We analyzed the differences in the mobility patterns and visualized the mobility flows, deliberating on what may be the potential impacts of building a bridge in the study area. Our methodology is general and can be applied in similar studies on different areas. However, the quality of results may depend on the available data.

cs.CY↗

arXiv2018

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

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.

cs.LG↗