English(EN) HRM-Text: Efficient Pretraining Beyond Scaling

HRM-Text模型大幅削减LLM预训练成本

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-20 01:59

研究人员开发了一种新颖的层次循环模型HRM-Text，它显著减少了预训练大型语言模型所需的计算资源和训练数据。通过将计算分解为策略层和执行层，并专门在指令-响应对上进行训练，一个10亿参数的模型在多个基准测试中取得了有竞争力的性能，而使用的token和计算量仅为标准模型的一小部分。这种方法通过降低从头开始预训练的门槛，使基础LLM研究更加易于获得。 AI

影响使更多研究人员能够从头开始训练基础模型，可能加速创新。

排序理由该集群包含一篇详细介绍新模型架构及其在基准测试中性能的学术论文。[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 →

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模型架构及其在基准测试中性能的学术论文。[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, infra; 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.CL TIER_1 English(EN) · Yasin Abbasi Yadkori · 2026-05-20 01:59

HRM-Text：超越扩展的高效预训练

The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological systems demonstrate highly sample-efficient learning through multi-timescale processi…

本文如何被排名

报道来源 [1]

HRM-Text：超越扩展的高效预训练

相关实体

相关话题