ARC 是一个视觉问题！
ARC Is a Vision Problem!
把 ARC 的网格谜题当作图像到图像转换任务，用原生 ViT 在「画布」表示上从零训练并在测试时训练中泛化到新任务，为视觉研究者提供了一个用纯视觉范式做抽象推理的可复用设定与基线。
原文依据 we formulate ARC within a vision paradigm, framing it as an image-to-image translation problem
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论抽象与推理语料库（ARC）旨在推动对抽象推理的研究，而抽象推理是人类智能的一个基本方面。针对 ARC 的常见方法将其视为一个语言导向的问题，由大语言模型（LLM）或循环推理模型来解决。然而，尽管 ARC 中类似谜题的任务本质上是视觉性的，现有研究却很少从以视觉为中心的视角来处理该问题。在本工作中，我们在视觉范式内对 ARC 进行形式化，将其界定为一个图像到图像转换问题。为了引入视觉先验，我们将输入表示在一块「画布」上，使其可以像自然图像一样被处理。这样一来，我们便可以直接应用标准的视觉架构，例如原生 Vision Transformer（ViT），来执行图像到图像的映射。我们的模型仅使用 ARC 数据从零开始训练，并通过测试时训练泛化到未见过的任务。我们的框架被称为 Vision ARC（VARC），在 ARC-1 基准上达到 60.4% 的准确率，大幅优于同样从零开始训练的现有方法。我们的结果与领先的 LLM 相比具有竞争力，并缩小了与人类平均表现之间的差距。
英文原文摘要 1197 字符
The Abstraction and Reasoning Corpus (ARC) is designed to promote research on abstract reasoning, a fundamental aspect of human intelligence. Common approaches to ARC treat it as a language-oriented problem, addressed by large language models (LLMs) or recurrent reasoning models. However, although the puzzle-like tasks in ARC are inherently visual, existing research has rarely approached the problem from a vision-centric perspective. In this work, we formulate ARC within a vision paradigm, framing it as an image-to-image translation problem. To incorporate visual priors, we represent the inputs on a "canvas" that can be processed like natural images. It is then straightforward for us to apply standard vision architectures, such as a vanilla Vision Transformer (ViT), to perform image-to-image mapping. Our model is trained from scratch solely on ARC data and generalizes to unseen tasks through test-time training. Our framework, termed Vision ARC (VARC), achieves 60.4% accuracy on the ARC-1 benchmark, substantially outperforming existing methods that are also trained from scratch. Our results are competitive with those of leading LLMs and close the gap to average human performance.