Alert button
Picture for Loic Houmard

Loic Houmard

Alert button

Visual Abstraction and Reasoning through Language

Mar 07, 2023
Giacomo Camposampiero, Loic Houmard, Benjamin Estermann, Joël Mathys, Roger Wattenhofer

Figure 1 for Visual Abstraction and Reasoning through Language
Figure 2 for Visual Abstraction and Reasoning through Language
Figure 3 for Visual Abstraction and Reasoning through Language
Figure 4 for Visual Abstraction and Reasoning through Language

While Artificial Intelligence (AI) models have achieved human or even superhuman performance in narrowly defined applications, they still struggle to show signs of broader and more flexible intelligence. The Abstraction and Reasoning Corpus (ARC), introduced by Fran\c{c}ois Chollet, aims to assess how close AI systems are to human-like cognitive abilities. Most current approaches rely on carefully handcrafted domain-specific languages (DSLs), which are used to brute-force solutions to the tasks present in ARC. In this work, we propose a general framework for solving ARC based on natural language descriptions of the tasks. While not yet beating state-of-the-art DSL models on ARC, we demonstrate the immense potential of our approach hinted at by the ability to solve previously unsolved tasks.

* The first two authors have contributed equally to this work 
Viaarxiv icon