Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks

The paper introduces a Neuro‑Symbolic framework that integrates a Vision‑Language Model (VLM) for automatic induction of First‑Order Logic (FOL) rules with a Dynamic Logic Tensor Network (D‑LTN) for differentiable rule verification. In a closed iterative loop, the VLM proposes candidate rules (Think), the D‑LTN verifies them against visual embeddings (Verify), and failures guide the VLM to refine its hypotheses (Revise). Evaluated on the ViSudo‑PC benchmark across four visual domains, the system successfully induces Sudoku constraint rules from only three training examples and achieves AUC scores that match or surpass prior methods such as NeuPSL and LTN.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• llms
• rag
• multimodal
• benchmarks