面向视觉分词与生成的球面 Leech 量化
Spherical Leech Quantization for Visual Tokenization and Generation
把无参数量化统一到格编码框架下，用 Leech 格（Λ24）在高维球面上做均匀量化，可直接替换 BSQ 等无查找量化器嵌入自回归图像生成与压缩管线，简化训练配方并改善重建-压缩折中。
原文依据 we find the Leech lattice-based quantization method, which is dubbed as Spherical Leech Quantization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无查找量化因其参数效率高、可扩展到大码本而受到广泛关注。本文通过格编码的视角，给出了不同非参数量化方法的统一表述。格码的几何性质解释了在使用 BSQ 等现有无查找量化变体训练自编码器时辅助损失项的必要性。在此基础上，我们探索了几种可能的候选方案，包括随机格、广义 Fibonacci 格以及最密球堆积格。其中我们发现，基于 Leech 格的量化方法（称为球面 Leech 量化，Λ24-SQ）得益于其在超球面上的高度对称性与均匀分布，既简化了训练配方，又改善了重建-压缩折中。在图像分词与压缩任务中，该量化方法在所有指标上的重建质量均优于最优的现有方法 BSQ，同时消耗的比特数还略少。这一改进同样可扩展到最优的自回归图像生成框架中。
英文原文摘要 1172 字符
Lookup-free quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of different non-parametric quantization methods through the lens of lattice coding. The geometry of lattice codes explains the necessity of auxiliary loss terms when training auto-encoders with certain existing lookup-free quantization variants such as BSQ. As a step forward, we explore a few possible candidates, including random lattices, generalized Fibonacci lattices, and densest sphere packing lattices. Among all, we find the Leech lattice-based quantization method, which is dubbed as Spherical Leech Quantization (\Lambda_ 24 -SQ), leads to both a simplified training recipe and an improved reconstruction-compression tradeoff thanks to its high symmetry and even distribution on the hypersphere. In image tokenization and compression tasks, this quantization approach achieves better reconstruction quality across all metrics than BSQ, the best prior art, while consuming slightly fewer bits. The improvement also extends to state-of-the-art auto-regressive image generation frameworks.