研究人员开发了一种新方法来加速离散自回归归一化流（一种生成模型）的推理。所提出的选择性Jacobi解码技术通过选择性地使用Jacobi解码来实现并行迭代优化，从而在不牺牲质量的情况下将生成速度提高了4.7倍。另一篇论文探讨了使用Wasserstein梯度流学习离散自回归先验，旨在通过在训练期间匹配分布来提高图像分词器与生成模型之间的兼容性。 AI
影响 这些论文介绍了提高生成模型效率和质量的技术，可能对未来在图像生成和其他领域的研发和应用产生影响。
排序理由 该集群包含两篇学术论文，详细介绍了生成模型和离散自回归先验方面的新颖方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.06148v1 Announce Type: cross Abstract: Discrete image tokenizers are commonly trained in two stages: first for reconstruction, and then with a prior model fitted to the frozen token sequences. This decoupling leaves the tokenizer unaware of the model that will later ge…
arXiv:2505.24791v2 Announce Type: replace Abstract: Discrete normalizing flows are promising generative models with advantages such as analytical log-likelihood computation and end-to-end training. However, the architectural constraints to ensure invertibility and tractable Jacob…
Discrete image tokenizers are commonly trained in two stages: first for reconstruction, and then with a prior model fitted to the frozen token sequences. This decoupling leaves the tokenizer unaware of the model that will later generate its tokens. As a result, the learned tokens…