English(EN) Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse

FlowVQ 引入新颖矢量量化方法以防止码本坍塌

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员引入了 FlowVQ，这是一种新颖的矢量量化方法，旨在克服传统 VQ-VAE 方法的局限性，例如码本坍塌和低效的码本使用。FlowVQ 将神经量化构建为联合建模和聚类过程，利用概率流 ODE 来传输源分布并保留概率质量。该方法通过传输分位数划分的先验码并获得诱导分布下的 Voronoi 中心来定义结构化码本。在图像标记化、生成和高精度标记化任务上的评估表明，FlowVQ 具有可扩展性，并通过充分利用提高了码本的表达能力。 AI

影响引入了一种更有效、可扩展的离散表示学习方法，有望改进生成模型。

排序理由该集群包含一篇详细介绍矢量量化新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍矢量量化新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yuwei Zeng, Zekun Shi · 2026-10-28 04:00

Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse

arXiv:2610.34828v1 Announce Type: new Abstract: Effective discrete representation learning with VQ-VAE serves as a fundamental component of modern autoregressive generative models. However, it is widely known to suffer from codebook collapse and inefficient code utilization. To a…

本文如何被排名

报道来源 [1]

Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse

相关实体

相关话题