English(EN) Complex-Valued Phase-Coherent Transformer

相干Transformer推动复值神经网络发展

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-11 07:38

研究人员开发了一种名为相干Transformer（PCT）的新型神经网络架构。该模型修改了标准Transformer的注意力机制，以更好地在层间保留相位信息，这对于某些类型的计算至关重要。实验表明，PCT在涉及长程记忆和推理的基准测试中，优于现有的实值和复值Transformer，并且在更深层时不会出现精度下降。 AI

影响引入了一种新颖的架构，提高了复值Transformer的泛化能力，可能影响未来需要相位敏感计算任务的模型设计。

排序理由该集群包含一篇详细介绍新型模型架构的学术论文。[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: 0 / 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新型模型架构的学术论文。[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: 141 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Leona Hioki · 2026-05-11 07:38

复数值相干Transformer

Complex-valued Transformers have largely inherited softmax attention from real-valued architectures. However, row-normalised token competition is not necessarily aligned with phase-preserving computation. In this paper, we introduce the Phase-Coherent Transformer (PCT), which app…

本文如何被排名

报道来源 [1]

复数值相干Transformer

相关实体

相关话题