TNO-QA: Tensor-Network Optimized Quantum Attention

We propose Tensor-Network Optimized Quantum Attention (TNO-QA), a hybrid quantum-classical framework that reduces the parameter overhead of classical attention mechanisms. TNO-QA combines low-rank tensor parameterization with a Quantum Train module to form a compact yet expressive attention block. In this design, Tensor-Train (TT) cores generate parameters for a fixed Parameterized Quantum Circuit (PQC) within the quantum train, whose outputs are processed by the associated Multi-Layer Perceptron (MLP) to produce the attention weights. This approach enables fully differentiable optimization in the classical domain, while the quantum circuit operates only in the forward pass, mitigating barren plateaus and quantum noise. A batched parameter generation scheme further reduces qubit requirements logarithmically, enhancing scalability. We integrate TNO-QA into U-Net architectures for diffusion models and evaluate on CIFAR-10, MNIST, and FMNIST. Experiments demonstrate$57-65 \%$reduction in attention parameters while maintaining comparable reconstruction quality and improving Fréchet Inception Distance relative to classical attention. TNO-QA is architecture-agnostic and supports multi-scale attention hierarchies, providing a scalable, stable, and hardware-efficient pathway toward practical quantum-assisted deep learning.