English(EN) An Input-Dependent Readout Phase for Resonant Sequence Models

共振序列模型获得依赖于输入的记忆读出能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

研究人员为共振序列模型开发了一种依赖于输入的读出阶段，增强了其保持长期记忆的能力。此修改允许模型根据当前输入调整其记忆检索，解决了先前固定转换模型的局限性。在 WikiText-2 上的字符级模型实验中，这种新方法显著提高了困惑度得分，尤其是在测试长于训练期间使用的序列时。 AI

影响引入了一种改进序列模型长期记忆的方法，可能提高需要扩展上下文的任务的性能。

排序理由详细介绍序列模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍序列模型新方法的学术论文。[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: 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。

arXiv cs.CL TIER_1 English(EN) · Shivesh Rane · 2026-10-12 04:00

用于共振序列模型的输入相关读出阶段

arXiv:2610.12496v1 Announce Type: cross Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives content-dependent memory at the cost of FFT-based training, while a fixed transitio…