October 13, 2025
Quantum machine learning and simulation: Practical insights for IT leaders
by Slawomir Folwarski, Senior Analytics Platform Architect, DXC and Dr. Angan Mitra, Principal AI Architect, DXC
Why quantum matters now
Quantum computing is no longer a distant curiosity; it’s moving from theory to practical pilots and real enterprise impact. Instead of relying solely on binary states, quantum systems utilize superposition and entanglement to perform massively parallel calculations. The promise: Exponential speedups for workloads that overwhelm classical systems.
DXC Technology has been testing the potential of quantum machine learning (QML) and simulation for years, building proofs of concept with clients and partners. This work illustrates how quantum technology can tackle data bottlenecks and accelerate AI (even with today’s limited hardware), while laying a foundation for what’s coming next.
Testing in the real world: The Airbus BMW Challenge
One proving ground was the 2024 Airbus BMW Quantum Computing Challenge (ABQCC). DXC teamed up with QuanIT and Kipu Quantum to propose two solutions:
- Quantum-enhanced autonomy: Using GenAI and quantum models to create realistic training images for autonomous vehicles and aircraft.
- Quantum-powered logistics: Aiming for a more efficient and sustainable supply chain.
This project demonstrated how quantum can enhance AI, particularly where data scarcity limits progress. As a result, our joint team was named a finalist in the autonomy stream.
Tackling the data bottleneck in autonomy
Training self-driving systems requires huge datasets. Simulation helps, but it can’t fully replace real-world recordings under varied conditions, e.g., the same street at noon and midnight. Consequently, the challenge was to transform images across conditions so that models can learn safely and reliably.
That’s where quantum generative adversarial networks (qGANs) come in. By fusing classical GANs with quantum algorithms, DXC’s team showed it’s possible to generate convincing day-to-night (or night-to-day) transformations without needing duplicate real-world captures.
How qGANs work in practice
The architecture pairs a standard neural network generator with a quantum discriminator. The generator produces synthetic images, while the discriminator (running on a quantum circuit) compares them to originals and refines the results. Key steps include:
Encoding the image into quantum states
Running quantum operations (such as Fourier transforms or controlled-SWAP gates)
Measuring output and decoding results back into classical form
Figure 1. qGAN hybrid architecture, classical generator supported by quantum discriminator
DXC’s team built this on AWS Braket with hybrid jobs; however, the approach is portable to other platforms, such as IBM Qiskit or CUDA-Q-based simulators.
Early findings
The experiments confirmed that hybrid quantum-classical setups can work today, even with limited quantum hardware.
Figure 2. Effects of qubits on hybrid optimization
Three takeaways:
Convergence: Loss functions improved significantly within 200 epochs, with more qubits (4, 8, 16) speeding up convergence.
Performance trade-offs: Local simulators were fastest but capped at around 20 qubits. Real quantum backends, such as those provided by Braket (like Rigetti Ankaa-3 and IQM Garnet), had slower runtimes and limited uptime.
Hybrid dependence: Training leaned heavily on GPUs, showing that classical horsepower still carries most of the load while quantum provides targeted boosts.
The tests also highlighted a significant reality. Encoding and decoding data into quantum states eats into expected gains. However, that doesn’t erase the value; it just means hardware maturity and smarter pipelines will matter just as much as algorithms.
Challenges to bear in mind
Quantum is not plug-and-play yet. CIOs and architects weighing their options should consider the following:
Hardware access: Real QPUs are scarce, with limited uptime and varying reliability across providers.
Integration overhead: Data encoding and hybrid job orchestration add friction.
Skills gap: Successful projects demand teams that blend quantum physics, ML and domain knowledge.
The path is clear. Each jump in qubit count and stability expands what’s feasible, moving quantum closer to mainstream IT strategy.
Put this knowledge to work
DXC’s work in the ABQCC and beyond shows that QML and simulation are no longer just science projects. They’re early-stage tools with real enterprise potential.
The quantum journey may be a bumpy ride, but the rewards could be transformative.
For CIOs and IT strategists, now is the time to get familiar, identify relevant workloads and build multidisciplinary teams that can translate quantum’s promise into better business outcomes.
Airbus-BMW Group Quantum Computing Challenge
DXC Technology teamed up with QuanIT and Kipu Quantum to propose a quantum-enhanced autonomy solution. The joint team was named a finalist for demonstrating how to use GenAI and quantum models to create realistic training images for autonomous vehicles and aircraft.
What IT leaders should take away
Experimentation is now possible: Cloud services like AWS Braket, CUDA-Q and IBM Qiskit enable teams to run small quantum workloads alongside classical ML.
Hybrid is the workable model: Expect classical and quantum to work in tandem for the foreseeable future.
Use cases are emerging: From safer autonomy to faster financial modeling, early pilots are showing where quantum delivers unique value.
About the authors
Slawomir Folwarski is the senior Analytics Platform architect at DXC Technology and a member of the Data & AI and Quantum Practices, where he focuses on analytics platform architecture and quantum computing. Sławomir has over 20 years of experience in the automotive, telco, public sector, logistics and finance industries. He teaches and evangelizes QC technology, contributing to events like the Airbus BMW QC Challenge and DXC’s Innovation Week and Technothon. Since January 2023, Slawomir has been pursuing his doctorate degree in quantum computing at Capitol Technology University. He also completed the IBM Quantum Challenge Fall 2022.
Dr. Angan Mitra is a Principal AI Architect at DXC Technology, specializing in GenAI solutions and quantum computing. His doctorate in Artificial Intelligence from the University of Grenoble and INRIA, France, complements more than a decade of research and innovation experience in academia and industry. Angan has contributed extensively to advancements in the automotive, smart city and financial sectors, with a focus on applying cutting-edge AI to complex real-world challenges. He continues to lead the development of intelligent systems that help organizations innovate and scale their operations.
