马尔可夫尺度预测：视觉自回归生成的新时代
Markovian Scale Prediction: A New Era of Visual Autoregressive Generation
将VAR的全上下文依赖重构为马尔可夫过程，用滑动窗口压缩历史尺度为紧凑向量，在保持生成质量的同时大幅降低显存和计算开销，为视觉自回归生成提供了更可扩展的框架。
原文依据 we treat each scale as a Markov state and introduce a sliding window that compresses certain previous scales into a compact history vector
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于下一尺度预测的视觉自回归建模（VAR）重振了自回归视觉生成。尽管其全上下文依赖（即建模所有先前尺度以进行下一尺度预测）通过利用完整信息流促进了更稳定和全面的表征学习，但由此产生的计算低效和巨大开销严重阻碍了VAR的实用性和可扩展性。这促使我们开发一种无需全上下文依赖、具有更好性能和效率的新VAR模型。为此，我们将VAR重新表述为非全上下文马尔可夫过程，提出Markov-VAR。它通过马尔可夫尺度预测实现：我们将每个尺度视为一个马尔可夫状态，并引入滑动窗口，将某些先前尺度压缩为紧凑的历史向量，以补偿因非全上下文依赖导致的历史信息损失。将历史向量与马尔可夫状态结合，产生一个在马尔可夫过程下演化的代表性动态状态。大量实验表明，Markov-VAR极其简单却高效：在ImageNet上，与VAR相比，Markov-VAR将弗雷歇初始距离降低10.5%（256x256），并将峰值内存消耗减少83.8%（1024x1024）。我们相信Markov-VAR可以作为未来视觉自回归生成及其他下游任务研究的基础。项目页面。
英文原文摘要 1422 字符
Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previous scales for next-scale prediction, facilitates more stable and comprehensive representation learning by leveraging complete information flow, the resulting computational inefficiency and substantial overhead severely hinder VAR's practicality and scalability. This motivates us to develop a new VAR model with better performance and efficiency without full-context dependency. To address this, we reformulate VAR as a non-full-context Markov process, proposing Markov-VAR. It is achieved via Markovian Scale Prediction: we treat each scale as a Markov state and introduce a sliding window that compresses certain previous scales into a compact history vector to compensate for historical information loss owing to non-full-context dependency. Integrating the history vector with the Markov state yields a representative dynamic state that evolves under a Markov process. Extensive experiments demonstrate that Markov-VAR is extremely simple yet highly effective: Compared to VAR on ImageNet, Markov-VAR reduces FID by 10.5% (256x256) and decreases peak memory consumption by 83.8% (1024x1024). We believe Markov-VAR can serve as a foundation for future research on visual autoregressive generation and other downstream tasks. Project Page.