用语言模型解拼图，把拼图块变符号序列来推理。
PuzLM: Solving Jigsaw Puzzles with Sequence-to-Sequence Language Models
- 将拼图块转为离散符号序列，用语言模型建模拼图逻辑。
- 在边界磨损或缺块情况下仍实现更优重建精度。
- 适合对符号推理和生成模型感兴趣的读者。
方块拼图通常通过视觉匹配拼图块图像来恢复原始布局。本文提出PuzLM，一种新视角：将拼图重装问题重构为离散序列到序列（Seq2Seq）任务，受自然语言表示启发。我们设计了一种高效的拼图量化方法，将每块转换为短的离散标记序列，使标准Seq2Seq语言模型可直接作为强大的拼图求解器使用。该方法表明，仅通过离散表示的符号推理即可实现高精度拼图重建，即使在边界侵蚀或缺失拼图块的情况下也优于现有最先进水平。
原文摘要 · Abstract (English)
Square jigsaw puzzles are typically solved by visually matching piece images to recover the original layout. This work introduces PuzLM, an alternative perspective that recasts jigsaw reassembly as a discrete sequence-to-sequence (Seq2Seq) problem, inspired by natural language representations. We design an efficient puzzle quantization procedure that transforms each piece into a short sequence of discrete tokens, enabling the direct application of standard Seq2Seq language models as powerful jigsaw solvers. Our approach demonstrates that accurate puzzle reconstruction can be achieved through purely symbolic reasoning over discrete representations, improving state-of-the-art performance even on puzzles with eroded boundaries or missing pieces.
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。