γILP is a differentiable pipeline for inducing first-order rules from unlabeled image data, showing strong performance on symbolic relational datasets, relational images, and pure image datasets such as Kandinsky patterns.
Logicot: Logical chain-of-thought instruction tuning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Visual Perceptual to Conceptual First-Order Rule Learning Networks
γILP is a differentiable pipeline for inducing first-order rules from unlabeled image data, showing strong performance on symbolic relational datasets, relational images, and pure image datasets such as Kandinsky patterns.