Project summary
The “Machine Learning for Quantum Simulations with Rydberg Atoms (ML-QSIM)” project addresses a central challenge in the current quantum revolution: the integration of advanced Artificial Intelligence and Machine Learning (AI/ML) techniques with Rydberg-atom quantum simulators, one of the most promising architectures for scalable quantum technologies. The coordinated initiative brings together four leading research nodes –CINN (Asturias, coordinator), INMA (Aragon), ICMM (Madrid), and CVC (Catalonia)– to simultaneously advance quantum hardware, theoretical modeling, hybrid simulation frameworks, and quantum algorithms tailored to next-generation analog quantum devices.
The proposal responds to a strategic scientific need: to identify where quantum devices can outperform state-of-the-art classical and AI-enhanced methods, to improve the stability and performance of emerging quantum platforms, and to develop quantum algorithms with real applicability in fields such as combinatorial optimization, quantum chemistry, complex materials, and computer vision.
The QML-CVC will open positions addressed for x1 postdoctoral researcher and x1 phd student interested in joining the team.
For more info, please address Dr. Fernando Vilariño (PI of the QML-CVC group) at fernando@cvc.uab.es.
Context
The 4-year project ” has been granted with 2 million euros by the Spanish Ministry of Science, Innovation and Universities, within the call of Projects in the Field of Artificial Intelligence 2025. QML-CVC and the rest of the institutions will contribute with the following tasks:
- QML-CVC: “Explanatory pathways for application in computer vision in quantum machine learning”
- CINN: “Using cold atoms with and for Machine Learning”
- INMA: “Scalable QUantum Ansätze with Deep learning”
- ICMM: “Quantum Algorithms for machine learning and optimization with Rydberg atoms”
QML-CVC Research
CVC provides the algorithmic backbone and the application-driven vision needed to unlock the full potential of the Rydberg-atom simulator and the new quantum algorithms developed in ML-QSIM. Its contributions can be summarized in four pillars: 1) Support for the tak AI-enhanced quantum hardware task (control, calibration, readout, holography), 2) Hybrid and advanced ML–quantum algorithm design, integrating methods across the different tasks, 3) The development of exploratory quantum pathways in computer vision, core contributuiion opening new research horizons, 4) Providing support to Impact, talent, and innovation, with events, connection to industry and webinar recordings, ensuring relevance beyond academia.
The QML-CVC node thus acts as both a scientific catalyst and an innovation engine, enabling ML-QSIM to move from fundamental quantum research to meaningful, cross-domain applications.