4 papers
DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding
Kin Ian Lo, Hala Hawashin, Mina Abbaszadeh +3
Recent vision-language models excel at large-scale image-text alignment but often neglect the compositional structure of language, leading to failures on tasks that hinge on word o…
Compositional Concept Generalization with Variational Quantum Circuits
Hala Hawashin, Mina Abbaszadeh, Nicholas Joseph +3
Compositional generalization is a key facet of human cognition, but lacking in current AI tools such as vision-language models. Previous work examined whether a compositional tenso…
Multimodal Structure-Aware Quantum Data Processing
Hala Hawashin, Mehrnoosh Sadrzadeh
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,…
Quantum-Like Contextuality in Large Language Models
Kin Ian Lo, Mehrnoosh Sadrzadeh, Shane Mansfield
Contextuality is a distinguishing feature of quantum mechanics and there is growing evidence that it is a necessary condition for quantum advantage. In order to make use of it, res…