Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle
This work addresses the challenge of achieving human-level intelligence in AI through a novel approach to the ARC benchmark, which is incremental in applying existing principles to a new model type.
The authors tackled the Abstraction and Reasoning Corpus (ARC) benchmark by introducing object-centric models aligned with human-like reasoning, using the Minimum Description Length principle for efficient search, and solved a diverse range of tasks while demonstrating generality in a different domain.
The Abstraction and Reasoning Corpus (ARC) is a challenging benchmark, introduced to foster AI research towards human-level intelligence. It is a collection of unique tasks about generating colored grids, specified by a few examples only. In contrast to the transformation-based programs of existing work, we introduce object-centric models that are in line with the natural programs produced by humans. Our models can not only perform predictions, but also provide joint descriptions for input/output pairs. The Minimum Description Length (MDL) principle is used to efficiently search the large model space. A diverse range of tasks are solved, and the learned models are similar to the natural programs. We demonstrate the generality of our approach by applying it to a different domain.