ProductsIndustry trialsResearchMachine LearningOptimizationEcosystem
Kipu Quantum missions by stage
Machine Learning
Lifting the accuracy of models industry already runs.
- Machine Learning, Products (Rimay): One tool call to improve the prediction of production models.
- Rimay extracts quantum features from tabular data and hands them back to your existing models. The quantum processor is used only in training; inference stays fully classical with millisecond response times. Rimay Quantum Feature Extraction
- Machine Learning, Industry trials (Rimay): Prove the predictive power on industry applications.
- Live engagements test the lift on the customer's own data: intent prediction in financial-services customer operations, and predictive maintenance on industrial sensor data. The same approach is measured on public benchmarks: 87 percent on satellite images where a ResNet-50 baseline reaches 83, and 84 with transfer learning, and on motor-imagery EEG, in peer-reviewed work by Mayo Clinic, 88.8 percent accuracy at an AUROC of 0.962 on a held-out participant. Rimay Quantum Feature Extraction Quantum-enhanced satellite image classification Mayo Clinic Proceedings: EEG motor-imagery classification
- Machine Learning, Research: Quantum features for the hardest classification problems.
- Digitized counterdiabatic quantum feature extraction is the peer-reviewed method underneath the trials. Every deployment is built as a surrogate: the quantum processor trains once on a representative subsample, and every production inference afterwards runs classically, with no quantum computer in the loop. On the satellite benchmark that design captured the same accuracy after training with five times fewer quantum executions. Current work extends the capability to thermographic drone imagery and time-series data. Scientific Reports: Digitized counterdiabatic quantum feature extraction
Optimization
Solving scheduling, routing and allocation at industrial scale.
- Optimization, Products (Iskay): Solve binary optimization problems with QPUs.
- Iskay is based on Kipu's bias-field counterdiabatic algorithm. It is validated on 156 IBM qubits against higher-order spin-glass instances, beating QAOA, quantum annealing, simulated annealing and Tabu search. All it takes is your objective function and preferred QPU from the IBM Quantum Cloud. Iskay Quantum Optimizer
- Optimization, Industry trials (Iskay): Industry applications build HUBO formulation expertise.
- A hundred-site routing problem needs roughly five million qubits as QUBO, but about a thousand expressed natively as HUBO. Partners are testing where that crossover lands on their own problems, starting at small representative problem instances and scaling later. Iskay Quantum Optimizer
- Optimization, Research: Keep the advantage as problems grow denser, not just larger.
- On an end-to-end benchmark of higher-order (HUBO) problems, a single QPU attempt is competitive with classical solvers running on 128 vCPUs or 8 NVIDIA A100 GPUs. From the Heron r3 processor clocking in kilohertz against classical gigahertz clock speeds. Read about the peer-reviewed algorithm and the benchmark below. Communications Physics 8, 348 (2025) The Quest for Quantum Advantage: end-to-end benchmarking Nature Computational Science: The Quantum Optimization Benchmarking Library
Ecosystem
One place for industry to run quantum work.
- Ecosystem, Products (Kipu Quantum Hub): Infrastructure to reach industrial quantum usefulness.
- Kipu's Quantum Hub delivers our advanced optimization solver and feature extraction as managed services, reachable via API, your own AI agent, or the command line. It provides access to IBM, IonQ, Rigetti, IQM, QuEra, AQT and Quandela, alongside simulators and classical resources. All aligned via a unified orchestration layer for building hybrid quantum workflows. Kipu Quantum Hub
- Ecosystem, Industry trials (Kipu Academy): Training experts for industrial quantum usefulness.
- The Kipu Academy is built to take engineers and decision-makers from no quantum background to shipping on the Hub. Both a business track and a technical track run as self-paced material or as private cohorts with industrial partners. Participants leave with everything to present a quantum-centric pitch or build a quantum-centric application. Kipu Academy
- Ecosystem, Research: Turn ideas into running quantum services.
- Most people will never operate a quantum computer directly. Tinkuq matches your use cases against Kipu Hub Services and creates a plan; Paqari then builds and runs the application. Soon these agents will let all users ship quantum services and make tool calls on the Kipu Quantum Hub. Research-preview for testers available today. Paqari Tinkuq