Multimodal Structure-Aware Quantum Data Processing
This addresses the challenge of scalable structured data processing for multimodal AI applications, though it appears incremental as it builds on existing quantum translation methods.
The paper tackled the problem of processing multimodal text+image data with structured approaches, which stall on classical computers due to tensor size, by developing MultiQ-NLP, a framework that translates data to variational quantum circuits; the result was a model achieving par performance with state-of-the-art classical models on an image classification task.
While large language models (LLMs) have advanced the field of natural language processing (NLP), their "black box" nature obscures their decision-making processes. To address this, researchers developed structured approaches using higher order tensors. These are able to model linguistic relations, but stall when training on classical computers due to their excessive size. Tensors are natural inhabitants of quantum systems and training on quantum computers provides a solution by translating text to variational quantum circuits. In this paper, we develop MultiQ-NLP: a framework for structure-aware data processing with multimodal text+image data. Here, "structure" refers to syntactic and grammatical relationships in language, as well as the hierarchical organization of visual elements in images. We enrich the translation with new types and type homomorphisms and develop novel architectures to represent structure. When tested on a main stream image classification task (SVO Probes), our best model showed a par performance with the state of the art classical models; moreover the best model was fully structured.