Reconstructing Quantum Dot Charge Stability Diagrams with Diffusion Models

2026-03-27

AI Summary

This work addresses the critical scalability bottleneck posed by the prohibitively long measurement times required for high-resolution quantum dot charge stability diagrams (CSDs), particularly in emerging spin qubit architectures lacking direct charge sensing. To overcome this challenge, the study introduces— for the first time—a conditional diffusion generative model for CSD reconstruction, which accurately recovers essential physical features such as charge transition lines from only 4% of the original data. The approach significantly outperforms conventional interpolation methods under large-scale missing-data conditions. By employing a lightweight architecture and experimentally motivated masking strategies—including uniform grids and line scans—and training on approximately 9,000 CSD samples, the method drastically reduces characterization overhead while preserving the structural integrity and physical fidelity of the reconstructed diagrams.

Abstract

Efficiently characterizing quantum dot (QD) devices is a critical bottleneck when scaling quantum processors based on confined spins. Measuring high-resolution charge stability diagrams (or CSDs, data maps which crucially define the occupation of QDs) is time-consuming, particularly in emerging architectures where CSDs must be acquired with remote sensors that cannot probe the charge of the relevant dots directly. In this work, we present a generative approach to accelerate acquisition by reconstructing full CSDs from sparse measurements, using a conditional diffusion model. We evaluate our approach using two experimentally motivated masking strategies: uniform grid-based sampling, and line-cut sweeps. Our lightweight architecture, trained on approximately 9,000 examples, successfully reconstructs CSDs, maintaining key physically important features such as charge transition lines, from as little as 4\% of the total measured data. We compare the approach to interpolation methods, which fail when the task involves reconstructing large unmeasured regions. Our results demonstrate that generative models can significantly reduce the characterization overhead for quantum devices, and provides a robust path towards an experimental implementation.

Problem

• quantum dot
• charge stability diagram
• device characterization
• remote sensing
• scaling quantum processors

Innovation

• diffusion models
• quantum dot
• charge stability diagrams
• generative modeling
• sparse reconstruction