4 papers
Quantum Models with Multi-Stage Training for Compositional Concept Generalization
Mina Abbaszadeh, Matilda Karabina Moore, Mehrnoosh Sadrzadeh +1
Compositional Concept Generalization (CoCoGen), the ability to systematically recombine learned primitives in novel contexts, is a key challenge for multimodal learning. In this wo…
VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring
Kairui Zhang, Ziwen Yu, Zahraa S. Abdallah +1
Sparse autoencoders (SAEs) provide useful decompositions of Transformer residual streams, but their learned features are usually named post hoc rather than directly connected to th…
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…
Evaluating Compositional Generalisation in VLMs and Diffusion Models
Beth Pearson, Bilal Boulbarss, Michael Wray +1
A fundamental aspect of the semantics of natural language is that novel meanings can be formed from the composition of previously known parts. Vision-language models (VLMs) have ma…