NVIDIA· Updated
NVIDIA released Ising, the first open-source AI model family designed to automate quantum processor calibration and real-time error correction. By treating hardware management as an AI problem, these models reduce manual tuning from days to hours and improve error-correction accuracy by 3x.
Ising Calibration, a vision language model for tuning processors, and Ising Decoding, a 3D convolutional neural network for quantum error correction (identifying and fixing errors in quantum bits).Quantum processors are currently limited by noise and fragility, requiring constant manual calibration. NVIDIA is positioning AI as the "control plane" for these machines to transform them into reliable systems. The Ising Decoding model is 2.5x faster and 3x more accurate than pyMatching, the current industry standard for error correction.
You can access the models, training data, and workflows via GitHub, Hugging Face, or NVIDIA NIM microservices. These tools integrate with NVIDIA CUDA-Q and NVIDIA NVQLink hardware, allowing researchers to fine-tune models for specific quantum architectures while keeping proprietary data local.
Introducing NVIDIA Ising, the world’s first open AI models to accelerate the path to useful quantum computers. Researchers and enterprises can now use AI-powered workflows for scalable, high-performance quantum systems with quantum processor calibration capabilities and quantum error-correction decoding. Learn more: https://t.co/jWT7X73T89
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →
More like this
