UDiTQC: U-Net-Style Diffusion Transformer for Quantum Circuit Synthesis

TL;DR

UDiTQC introduces a novel U-Net-style Diffusion Transformer that enhances quantum circuit synthesis by effectively modeling global context and multi-scale features, outperforming existing methods in entanglement and unitary tasks.

Contribution

The paper presents a new U-Net-style Diffusion Transformer architecture tailored for quantum circuit synthesis, combining multi-scale feature extraction with global context modeling, and demonstrates its superiority over prior approaches.

Findings

Outperforms existing methods in entanglement generation

Achieves better results in unitary compilation tasks

Supports circuit masking and editing for physical property customization

Abstract

Quantum computing is a transformative technology with wide-ranging applications, and efficient quantum circuit generation is crucial for unlocking its full potential. Current diffusion model approaches based on U-Net architectures, while promising, encounter challenges related to computational efficiency and modeling global context. To address these issues, we propose UDiT,a novel U-Net-style Diffusion Transformer architecture, which combines U-Net's strengths in multi-scale feature extraction with the Transformer's ability to model global context. We demonstrate the framework's effectiveness on two tasks: entanglement generation and unitary compilation, where UDiTQC consistently outperforms existing methods. Additionally, our framework supports tasks such as masking and editing circuits to meet specific physical property requirements. This dual advancement, improving quantum circuit synthesis and refining generative model architectures, marks a significant milestone in the convergence of quantum computing and machine learning research.