PulseAugur
实时 09:27:10

新模型学习ARC基准的可视符号规则

研究人员开发了Loop-OWM,一种以对象为中心的世界建模架构,旨在学习Abstraction and Reasoning Corpus (ARC) 的规则。这个新模型将视觉符号规则学习为结构化状态之间的转换,并结合了颜色原型槽和循环转换模型。与具有相似或更少参数的现有方法相比,Loop-OWM在ARC-1和ARC-2基准测试中均表现出优越的性能。 AI

影响 引入了一种学习视觉符号规则的新方法,有可能提高AI从视觉模式中理解和泛化的能力。

排序理由 该集群包含一篇详细介绍特定AI基准新模型架构的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Gege Gao, Bernhard Sch\"olkopf, Andreas Geiger ·

    Slots, Transitions, Loops: Learning Composable World Models for ARC

    arXiv:2606.12316v1 Announce Type: new Abstract: ARC tests in-context rule induction: given a few input-output demonstrations, a model must infer the hidden rule and apply it to a new query. While many approaches express ARC rules through language, code, or symbolic programs, ARC …

  2. arXiv cs.CV TIER_1 English(EN) · Andreas Geiger ·

    Slots, Transitions, Loops: Learning Composable World Models for ARC

    ARC tests in-context rule induction: given a few input-output demonstrations, a model must infer the hidden rule and apply it to a new query. While many approaches express ARC rules through language, code, or symbolic programs, ARC itself is visual-symbolic: rules appear as grid …