Quantinuum researchers tackle AI’s ‘interpretability problem’, helping us build safer systems
The Artificial Intelligence (AI) systems that have recently permeated our lives have a serious problem: they are built in a way that makes them very hard - and sometimes impossible - to understand or interpret. Luckily, our team is tackling this problem, and we’ve just published a new paper that covers the issue in detail.
It turns out that the lack of explainability in machine learning (ML) models, such as ChatGPT or Claude, comes from the way that the systems are built. Their underlying architecture (a neural network) lacks coherent structure. While neural networks can be trained to effectively solve certain tasks, the way they do it is largely (or, from a practical standpoint, almost wholly) inaccessible. This absence of interpretability in modern ML is increasingly a major concern in sensitive areas where accountability is required, such as in finance and the healthcare and pharmaceutical sectors. The “interpretability problem in AI” is therefore a topic of grave worry for large swathes of the corporate and enterprise sector, regulators, lawmakers, and the general public.
These concerns have given birth to the field of eXplainable AI, or XAI, which attempts to solve the interpretability problem through so-called ‘post-hoc’ techniques (where one takes a trained AI model and aims to give explanations for either its overall behavior or individual outputs). This approach, while still evolving, has its own issues due to the approximate nature and fundamental limitations of post-hoc techniques.
The second approach to the interpretability problem is to employ new ML models that are, by design, inherently interpretable from the start. Such an interpretable AI model comes with explicit structure which is meaningful to us “from the outside”. Realizing this in the tech we use every day means completely redesigning how machines learn - creating a new paradigm in AI. As Sean Tull, one of the authors of the paper, stated: “In the best case, such intrinsically interpretable models would no longer even require XAI methods, serving instead as their own explanation, and one of a deeper kind.”
At Quantinuum, we’re continuing work to develop new paradigms in AI while also working to sharpen theoretical and foundational tools that allow us all to assess the interpretability of a given model. In our recent paper, we present a new theoretical framework for both defining AI models and analyzing their interpretability. With this framework, we show how advantageous it is for an AI model to have explicit and meaningful compositional structure.
The idea of composition is explored in a rigorous way using a mathematical approach called “category theory”, which is a language that describes processes and their composition. The category theory approach to interpretability can be accomplished via a graphical calculus which was also developed in part by Quantinuum scientists, and which is finding use cases in everything from gravity to quantum computing.
A fundamental problem in the field of XAI has been that many terms have not been rigorously defined, making it difficult to study - let alone discuss - interpretability in AI. Our paper presents the first known theoretical framework for assessing the compositional interpretability of AI models. With our team’s work, we now have a precise and mathematically defined definition of interpretability that allows us to have these critical conversations.
After developing the framework, our team used it to analyze the full spectrum of ML approaches. We started with Transformers (the “T” in ChatGPT), which are not interpretable – pointing to a serious issue in some of the world’s most widely used ML tools. This is in contrast with (sparse) linear models and decision trees, which we found are indeed inherently interpretable, as they are usually described.
Our team was also able to make precise how other ML models were what they call 'compositionally interpretable'. These include models already studied by our own scientists including DisCo NLP models, causal models, and conceptual space models.
Many of the models discussed in this paper are classical, but more broadly the use of category theory and string diagrams makes these tools very well suited to analyzing quantum models for machine learning. In addition to helping the broader field accurately assess the interpretability of various ML models, the seminal work in this paper will help us to develop systems that are interpretable by design.
This work is part of our broader AI strategy, which includes using AI to improve quantum computing, using quantum computers to improve AI, and – in this case - using the tools of category theory and compositionality to help us better understand AI.
About Quantinuum
Quantinuum, the world’s largest integrated quantum company, pioneers powerful quantum computers and advanced software solutions. Quantinuum’s technology drives breakthroughs in materials discovery, cybersecurity, and next-gen quantum AI. With over 500 employees, including 370+ scientists and engineers, Quantinuum leads the quantum computing revolution across continents.
If we are to create ‘next-gen’ AI that takes full advantage of the power of quantum computers, we need to start with quantum native transformers. Today we announce yet again that Quantinuum continues to lead by demonstrating concrete progress — advancing from theoretical models to real quantum deployment.
The future of AI won't be built on yesterday’s tech. If we're serious about creating next-generation AI that unlocks the full promise of quantum computing, then we must build quantum-native models—designed for quantum, from the ground up.
Around this time last year, we introduced Quixer, a state-of-the-art quantum-native transformer. Today, we’re thrilled to announce a major milestone: one year on, Quixer is now running natively on quantum hardware.
Why this matters: Quantum AI, born native
This marks a turning point for the industry: realizing quantum-native AI opens a world of possibilities.
Classical transformers revolutionized AI. They power everything from ChatGPT to real-time translation, computer vision, drug discovery, and algorithmic trading. Now, Quixer sets the stage for a similar leap — but for quantum-native computation. Because quantum computers differ fundamentally from classical computers, we expect a whole new host of valuable applications to emerge.
Achieving that future requires models that are efficient, scalable, and actually run on today’s quantum hardware.
That’s what we’ve built.
What makes Quixer different?
Until Quixer, quantum transformers were the result of a brute force “copy-paste” approach: taking the math from a classical model and putting it onto a quantum circuit. However, this approach does not account for the considerable differences between quantum and classical architectures, leading to substantial resource requirements.
Quixer is different: it’s not a translation – it's an innovation.
With Quixer, our team introduced an explicitly quantum transformer, built from the ground up using quantum algorithmic primitives. Because Quixer is tailored for quantum circuits, it's more resource efficient than most competing approaches.
As quantum computing advances toward fault tolerance, Quixer is built to scale with it.
What’s next for Quixer?
We’ve already deployed Quixer on real-world data: genomic sequence analysis, a high-impact classification task in biotech. We're happy to report that its performance is already approaching that of classical models, even in this first implementation.
This is just the beginning.
Looking ahead, we’ll explore using Quixer anywhere classical transformers have proven to be useful; such as language modeling, image classification, quantum chemistry, and beyond. More excitingly, we expect use cases to emerge that are quantum-specific, impossible on classical hardware.
This milestone isn’t just about one model. It’s a signal that the quantum AI era has begun, and that Quantinuum is leading the charge with real results, not empty hype.
Stay tuned. The revolution is only getting started.
Our team is participating in ISC High Performance 2025 (ISC 2025) from June 10-13 in Hamburg, Germany!
As quantum computing accelerates, so does the urgency to integrate its capabilities into today’s high-performance computing (HPC) and AI environments. At ISC 2025, meet the Quantinuum team to learn how the highest performing quantum systems on the market, combined with advanced software and powerful collaborations, are helping organizations take the next step in their compute strategy.
Quantinuum is leading the industry across every major vector: performance, hybrid integration, scientific innovation, global collaboration and ease of access.
- Our industry-leading quantum computer holds the record for performance with a Quantum Volume of 2²³ = 8,388,608 and the highest fidelity on a commercially available QPU available to our users every time they access our systems.
- Our systems have been validated by a #1 ranking against competitors in a recent benchmarking study by Jülich Research Centre.
- We’ve laid out a clear roadmap to reach universal, fully fault-tolerant quantum computing by the end of the decade and will launch our next-generation system, Helios, later this year.
- We are advancing real-world hybrid compute with partners such as RIKEN, NVIDIA, SoftBank, STFC Hartree Center and are pioneering applications such as our own GenQAI framework.
Exhibit Hall
From June 10–13, in Hamburg, Germany, visit us at Booth B40 in the Exhibition Hall or attend one of our technical talks to explore how our quantum technologies are pushing the boundaries of what’s possible across HPC.
Presentations & Demos
Throughout ISC, our team will present on the most important topics in HPC and quantum computing integration—from near-term hybrid use cases to hardware innovations and future roadmaps.
Multicore World Networking Event
- Monday, June 9 | 7:00pm – 9:00 PM at Hofbräu Wirtshaus Esplanade
In partnership with Multicore World, join us for a Quantinuum-sponsored Happy Hour to explore the present and future of quantum computing with Quantinuum CCO, Dr. Nash Palaniswamy, and network with our team.
Register here
H1 x CUDA-Q Demonstration
- All Week at Booth B40
We’re showcasing a live demonstration of NVIDIA’s CUDA-Q platform running on Quantinuum’s industry-leading quantum hardware. This new integration paves the way for hybrid compute solutions in optimization, AI, and chemistry.
Register for a demo
HPC Solutions Forum
- Wednesday, June 11 | 2:20 – 2:40 PM
“Enabling Scientific Discovery with Generative Quantum AI” – Presented by Maud Einhorn, Technical Account Executive at Quantinuum, discover how hybrid quantum-classical workflows are powering novel use cases in scientific discovery.
See You There!
Whether you're exploring hybrid solutions today or planning for large-scale quantum deployment tomorrow, ISC 2025 is the place to begin the conversation.
We look forward to seeing you in Hamburg!
Quantinuum has once again raised the bar—setting a record in teleportation, and advancing our leadership in the race toward universal fault-tolerant quantum computing.
Last year, we published a paper in Science demonstrating the first-ever fault-tolerant teleportation of a logical qubit. At the time, we outlined how crucial teleportation is to realize large-scale fault tolerant quantum computers. Given the high degree of system performance and capabilities required to run the protocol (e.g., multiple qubits, high-fidelity state-preparation, entangling operations, mid-circuit measurement, etc.), teleportation is recognized as an excellent measure of system maturity.
Today we’re building on last year’s breakthrough, having recently achieved a record logical teleportation fidelity of 99.82% – up from 97.5% in last year’s result. What’s more, our logical qubit teleportation fidelity now exceeds our physical qubit teleportation fidelity, passing the break-even point that establishes our H2 system as the gold standard for complex quantum operations.
This progress reflects the strength and flexibility of our Quantum Charge Coupled Device (QCCD) architecture. The native high fidelity of our QCCD architecture enables us to perform highly complex demonstrations like this that nobody else has yet to match. Further, our ability to perform conditional logic and real-time decoding was crucial for implementing the Steane error correction code used in this work, and our all-to-all connectivity was essential for performing the high-fidelity transversal gates that drove the protocol.
Teleportation schemes like this allow us to “trade space for time,” meaning that we can do quantum error correction more quickly, reducing our time to solution. Additionally, teleportation enables long-range communication during logical computation, which translates to higher connectivity in logical algorithms, improving computational power.
This demonstration underscores our ongoing commitment to reducing logical error rates, which is critical for realizing the promise of quantum computing. Quantinuum continues to lead in quantum hardware performance, algorithms, and error correction—and we’ll extend our leadership come the launch of our next generation system, Helios, in just a matter of months.