Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle

Sébastien Ferré

Résumé

The Abstraction and Reasoning Corpus (ARC) is a challenging benchmark, introduced to foster AI research towards human-like 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 natural programs.
Fichier principal
Vignette du fichier
paper.pdf (325.04 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04602995 , version 1 (06-06-2024)

Licence

Identifiants

  • HAL Id : hal-04602995 , version 1

Citer

Sébastien Ferré. Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle. IDA 2024 - Symposium on Intelligent Data Analysis, Apr 2024, Stockholm, Sweden. pp.1-12. ⟨hal-04602995⟩
32 Consultations
19 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More