Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks
A Neuro-Symbolic framework that closes this gap by tightly coupling a Vision-Language Model for automatic First-Order Logic rule induction with a Dynamic Logic Tensor Network for differentiable rule verification, in a closed iterative feedback loop is proposed.
Homayoun Afshari, Pietro Basci, A. Russo et al.
· 0 citations