PulseAugur
实时 06:45:06
English(EN) Squeezing More from Limited Data with Recursive Transformers

递归 Transformer 在有限数据上表现出改进的性能

研究人员开发了递归 Transformer,与标准 Transformer 相比,它们在数据有限的条件下表现更好。这些新模型重用共享块并采用因子化嵌入来优化参数使用并减少词汇映射参数。在各种数据预算和语料库上的实验表明,递归 Transformer 在使用 1000 万到 1 亿词进行训练时优于标准模型,并在 BabyLM 挑战赛 2025 中保持与顶级模型的竞争力。 AI

影响 为在有限数据集上训练语言模型提供了一种更有效的方法,有可能提高在数据稀缺环境中的性能。

排序理由 详细介绍新模型架构的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

递归 Transformer 在有限数据上表现出改进的性能

本文如何被排名

Signal score
27 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍新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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Serdar G\"ulbahar, Lukas Edman, Alexander Fraser ·

    利用有限数据通过递归 Transformer 提取更多信息

    arXiv:2608.26973v1 Announce Type: new Abstract: Pre-training under limited data requires a different view of scaling than web-scale language modeling. With a fixed data budget but relatively abundant compute, increasing parameter count helps only up to an optimal scale; beyond th…