New hybrid quantum applications show quantum computing’s ability to optimize materials science properties using Quantum-Enhanced Generative Adversarial Networks (QGANs) and fine-tune LLM models using Quantum Machine Learning (QML)
COLLEGE PARK, Md.–(BUSINESS WIRE)–IonQ (NYSE: IONQ), a leading commercial quantum computing and networking company, today announced new research advancements in applying quantum computing to artificial intelligence (AI) and Machine Learning, marking significant progress in hybrid quantum-classical approaches that enhance both large language models (LLMs) and generative AI.
Detailed in two new research papers, IonQ researchers demonstrated how quantum computing can support advanced materials development by generating synthetic images of rare anomalies and enhancing Large Language Models by adding a quantum layer for fine-tuning. These efforts reflect IonQ’s continued focus on practical, near-term commercial quantum applications in AI to drive value in data-scarce settings and for complex tasks.
Enhancing LLMs with Quantum Fine-Tuning for Improved Classification Accuracy
In a newly published paper, IonQ introduced a hybrid quantum-classical architecture designed to enhance LLM fine-tuning, where a pre-trained LLM is supplemented with a small set of training data to customize its functionality via quantum machine learning. To compare performance against classical methods, IonQ researchers took an open-source large language model that is widely used to predict words in a sentence, and incorporated a parameterized quantum circuit as a new layer. With this quantum fine-tuning step, the hybrid model was repurposed to understand sentence sentiment.
The resulting hybrid quantum approach outperformed classical-only methods in accuracy, surpassing classical methods that use a similar number of parameters by a meaningful margin. The researchers observed a trend of increase in classification accuracy with an increasing number of qubits. They also projected significant energy savings for inference using the hybrid quantum algorithm, relative to inference using all-classical models, as the problem size increases beyond 46 qubits. This paves the way for quantum-enhanced fine-tuning of broader classes of foundational AI models, including AI models for natural language processing, image processing, and property prediction in chemistry, biology and materials science.
“This work highlights how quantum computing can be strategically integrated into classical AI workflows, taking advantage of increased expressivity to enhance traditional AI LLMs in rare-data regimes,” said Masako Yamada, Director of Applications Development IonQ. “LLMs have demonstrated versatility far beyond pure ‘language’ applications, and we believe hybrid quantum-classical models are well positioned to unlock the next wave of AI capabilities.”
Pioneering Quantum Generative Modeling to Improve Material Properties
In a separate research publication, IonQ collaborated with a top-tier automotive manufacturer to apply quantum-enhanced generative adversarial networks (GANs) to materials science. Researchers trained GANs to sample the output distribution of a quantum circuit, generating synthetic images of steel microstructures that augment conventional imaging techniques, where data is often sparse, and therefore model trainability is poor.
The microstructure images produced using IonQ’s hybrid QGAN method achieved a higher quality score in up to 70% of cases when compared to images produced using baseline classical generative models. Industrial AI models often rely on proprietary data sets, which may result in lack of data, imbalance of data, or high costs in generating data. The ability to supplement image data is vital to developing AI models where the objective is to optimize manufacturing process parameters to result in material properties that meet stringent requirements.
“This work is a compelling example of how the combination of IonQ’s quantum computers and classical machine learning can produce impressive results for materials science and manufacturing,” said Ariel Braunstein, SVP of Product at IonQ. “Using classical computing to augment experimental data with synthetic generation can be expensive and limited in value. This work shows that a quantum hybrid approach can yield higher quality images with less data than classical methods and could lead to new applications across industries such as materials science, medical imaging, and financial forecasting.”
With its latest Forte Enterprise-class quantum computers, IonQ continues to push the boundaries with new capabilities that can outperform classical computing and provide opportunities to integrate AI. These research milestones follow IonQ’s recent announcement of a new quantum simulation tool with Ansys, which demonstrated improvements of up to 12% for workflows used in the Computer Aided Engineering industry. IonQ has also signed a memorandum of understanding (MOU) with AIST’s Global Research and Development Center for Business by Quantum AI (G-QuAT) to help advance hybrid quantum computing technologies with AI.
For more details, read the full technical papers on ArXiv:
- Quantum Large Language Model Fine-Tuning
- End-to-End Demonstration of Quantum Generative Adversarial Networks for Steel Microstructure Image Augmentation on Trapped-Ion Quantum Computer
About IonQ
IonQ, Inc. is a leader in the quantum computing and networking industries, delivering high-performance systems aimed at solving the world’s largest and most complex commercial and research use cases. IonQ’s current generation quantum computers, IonQ Forte and IonQ Forte Enterprise, are the latest in a line of cutting-edge systems, boasting 36 algorithmic qubits. The company’s innovative technology and rapid growth were recognized in Newsweek’s 2025 Excellence Index 1000, Forbes’ 2025 Most Successful Mid-Cap Companies list, and Built In’s 2025 100 Best Midsize Places to Work in Washington DC and Seattle, respectively. Available through all major cloud providers, IonQ is making quantum computing more accessible and impactful than ever before. Learn more at IonQ.com.
IonQ Forward-Looking Statements
This press release contains certain forward-looking statements within the meaning of Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended. Some of the forward-looking statements can be identified by the use of forward-looking words. Statements that are not historical in nature, including the terms “accessible,” “advancements,” “aimed,” “available,” “believe,” “can,” “could,” “cutting-edge,” “delivering,” “designed,” “drive,” “focus,” “growth,” “innovative,” “impactful,” “latest,” “leader,” “making,” “may,” “paves the way,” “pioneering,” “practical,” “progress,” “push,” “solving,” and other similar expressions are intended to identify forward-looking statements. These statements include those related to the IonQ’s quantum computing capabilities and plans; IonQ’s technology driving commercial quantum advantage in the future; the relevance, accuracy, quality, cost and energy efficiency, commercial-readiness, and utility of quantum algorithms and applications run on IonQ’s quantum computers; the commercial value, effectiveness, and future impacts of IonQ’s offerings available today; and the scalability, efficiency, viability, accessibility, effectiveness, importance, reliability, performance, speed, impact, practicality, feasibility, energy and cost savings, and commercial-readiness of IonQ’s offerings. Forward-looking statements are predictions, projections, and other statements about future events that are based on current expectations and assumptions and, as a result, are subject to risks and uncertainties. Many factors could cause actual future events to differ materially from the forward-looking statements in this press release, including but not limited to: IonQ’s ability to implement its technical roadmap; changes in the competitive industries in which IonQ operates, including development of competing technologies including algorithms; IonQ’s ability to deliver, and customers’ ability to generate, value from IonQ’s offerings; IonQ’s ability to deliver higher quality output with less data; changes in laws and regulations affecting IonQ’s and its suppliers’ businesses; IonQ’s ability to implement its business plans, forecasts, roadmaps and other expectations, to identify and realize partnerships and opportunities, and to engage new and existing customers; IonQ’s ability to deliver services and products within currently anticipated timelines; changes in laws and regulations affecting IonQ’s patents; and IonQ’s ability to maintain or obtain patent protection for its products and technology, including with sufficient breadth to provide a competitive advantage. You should carefully consider the foregoing factors and the other risks and uncertainties disclosed in the Company’s filings, including but not limited to those described in the “Risk Factors” section of IonQ’s most recent periodic financial report (10-Q or 10-K) filed by IonQ with the Securities and Exchange Commission. These filings identify and address other important risks and uncertainties that could cause actual events and results to differ materially from those contained in the forward-looking statements. Forward-looking statements speak only as of the date they are made. Readers are cautioned not to put undue reliance on forward-looking statements, and IonQ assumes no obligation and does not intend to update or revise these forward-looking statements, whether as a result of new information, future events, or otherwise. IonQ does not give any assurance that it will achieve its expectations. IonQ may or may not choose to practice or otherwise use the inventions described in the issued patents in the future.
Contacts
IonQ Media contact:
Jane Mazur
[email protected]
IonQ Investor Contact:
[email protected]
