Summary
Combining information from pictures and text is often done by simple math tricks, but this paper tries a new way using ideas from quantum computing. The authors built a hybrid system that processes visual and textual features using quantum circuits that mimic quantum entanglement, a special connection between quantum states. Their method, called QEMFN, mixes these features better than standard approaches when tested on popular image and text matching datasets. They carefully measured and analyzed what the quantum part contributes and even tested it on real quantum hardware, showing it could be used with current devices.
What this means in practice
- •For machine learning engineers: Use trainable quantum entanglement modules to improve fusion of image and text features for retrieval tasks.
- •For quantum computing developers: Implement and test hybrid quantum-classical fusion models on current superconducting quantum devices to study practical integration.
Abstract
Multimodal vision-language systems typically fuse image and text embeddings through classical operators such as concatenation, attention, bilinear pooling, or tensor interactions. We propose Quantum Entangled Multimodal Fusion Networks (QEMFN), a hybrid quantum-classical framework that introduces parameterized entanglement as a structured inductive bias for multimodal fusion. Pretrained visual and textual features are projected into compact latent spaces, encoded as angle-parameterized quantum states, processed through intra-modal and paired cross-modal entangling circuits, and measured to produce fused representations for retrieval. Under matched parameter budgets and identical frozen CLIP backbones, QEMFN outperforms classical fusion baselines on COCO-5k and Flickr30k, including multilayer perceptron, tensor fusion, FiLM, cross-attention, compact transformer, and a dequantized paired-topology analogue. An ablation suite isolates the quantum module's contribution from the surrounding classical projections, and quantum-centric analyses report Meyer-Wallach entangling capability, expressibility, gradient variance against barren-plateau bounds, and entropy-performance correlation under controls for training progress alongside an intervention study on the entangling component. QEMFN is executed under shot-based estimation, a noise-modeled fake backend, and a real superconducting device with zero-noise extrapolation. This work does not claim quantum computational advantage; the contribution is the framework together with a controlled empirical and quantum-centric evaluation that positions trainable entanglement as an interpretable, hardware-executable fusion mechanism at scales accessible on contemporary devices.