Research map / Image generation / Fast diffusion sampling
Quantum Generative Diffusion Model: A Fully Quantum-Mechanical Model for Generating Quantum State Ensemble
Chuangtao Chen, Qinglin Zhao, MengChu Zhou, Zhimin He, Zhili Sun, Haozhen Situ
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-step diffusion-denoising process (vs diffusion-free QuDT with same ansatz) (ablation) | QGDM · TFIM Gibbs state generation N=4 (gate noise 0.5%) | fidelity: 0.710 -> 0.913 | Improved |
| add multi-step diffusion-denoising process (vs QuDT) (ablation) | QGDM · TFIM Gibbs state generation N=4 (gate noise 1%) | fidelity: 0.697 -> 0.837 | Improved |
| add multi-step diffusion-denoising process (vs QuDT) (ablation) | QGDM · TFIM Gibbs state generation N=1 (gate noise 1%) | fidelity: 0.996 -> 0.995 | No clear effect |
| increase timestep embedding qubits N_tau up to N (ablation) | QGDM · Random pure state generation | fidelity | Improved |
| increase timestep embedding qubits N_tau beyond N (ablation) | QGDM · Random pure state generation | fidelity | Hurt |
| replace adversarial QGANs with diffusion on mixed states | RQGDM · Random mixed state generation N=8 | fidelity: 0.324 -> 0.993 | Improved |
| replace EQ-GAN with QGDM on pure states | QGDM · Random pure state generation N=4 | fidelity: 0.896 -> 0.996 | Improved |
| use QGDM instead of Hamiltonian-specialized VGSP in noiseless TFIM | QGDM · TFIM Gibbs state generation, mean over N (noiseless) | fidelity: 0.999 -> 0.996 | Hurt |
| use QGDM instead of VGSP under gate noise | QGDM · TFIM Gibbs state generation, mean over N (gate noise 1%) | fidelity: 0.908 -> 0.927 | Improved |
| use QGDM instead of VGSP under gate noise | QGDM · TFIM Gibbs state generation, mean over N (gate noise 0.5%) | fidelity: 0.954 -> 0.962 | Improved |
Closest papers by meaning
- One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective (NeurIPS 2026 · similarity 0.86)
- Understanding Diffusion Models by Feynman's Path Integral (ICML 2024 · similarity 0.85)
- Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine (NeurIPS 2026 · similarity 0.85)
- Online Learning of Pure States is as Hard as Mixed States (NeurIPS 2025 · similarity 0.84)
- Adversarial Schrödinger Bridge Matching (NeurIPS 2024 · similarity 0.84)
- BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
