English(EN) Optimal Transport Depth Up-Scaling

新方法利用最优传输高效扩展LLM深度

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

研究人员推出了一种名为最优传输深度升级（OT-DUS）的新颖方法，可用于高效地增加预训练大型语言模型（LLM）的规模。与现有的复制或平均层的方法不同，OT-DUS利用最优传输理论来对齐和融合功能上对应的神经元。这种方法旨在缓解由神经元排列不匹配引起的性能下降。实验表明，OT-DUS在通用和专业领域都优于当前方法，并且当新层插入到模型架构的更高层时，性能提升会增加。 AI

影响提供了一种更有效的扩展LLM的方法，可能降低训练成本并提高性能。

排序理由详细介绍LLM训练新方法的学术论文。[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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍LLM训练新方法的学术论文。[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: 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]

arXiv cs.CL TIER_1 English(EN) · Mingzi Cao, Xi Wang, Nikolaos Aletras · 2026-10-09 04:00

Optimal Transport Depth Up-Scaling

arXiv:2508.08011v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) from scratch at larger scales yields remarkable performance but incurs substantially high training costs. Depth up-scaling provides an efficient alternative by inserting new layers into …

本文如何被排名

报道来源 [1]

Optimal Transport Depth Up-Scaling

相关实体

相关话题