探索神经引导程序归纳在ARC-AGI中的高效性与泛化能力
Towards Efficient Neurally-Guided Program Induction for ARC-AGI
- 对比学习网格空间、程序空间与变换空间三种方法
- 发现程序空间方法泛化性能更优，但效率较低
- 提出变换空间新思路，适合追求高效泛化的研究者
ARC-AGI是一个开放世界问题领域，其关键能力在于分布外泛化。在程序归纳范式下，本文通过一系列实验揭示了不同神经引导程序归纳方法的效率与泛化特性。研究考虑三种范式：学习网格空间、学习程序空间、学习变换空间。对前两种方法进行了全面实现与实验，其中程序空间方法保留用于提交ARC-AGI挑战。基于对两者的优劣分析，提出第三种范式作为潜在解决方案，并开展了初步实验。
原文摘要 · Abstract (English)
ARC-AGI is an open-world problem domain in which the ability to generalize out-of-distribution is a crucial quality. Under the program induction paradigm, we present a series of experiments that reveal the efficiency and generalization characteristics of various neurally-guided program induction approaches. The three paradigms we consider are Learning the grid space, Learning the program space, and Learning the transform space. We implement and experiment thoroughly on the first two, and retain the second one for ARC-AGI submission. After identifying the strengths and weaknesses of both of these approaches, we suggest the third as a potential solution, and run preliminary experiments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。