PulseAugur
实时 06:29:36
Română(RO) A.X K2 Technical Report

A.X K2 语言模型发布,拥有 6880 亿参数并专注于智能体应用

一份新的技术报告介绍了 A.X K2,一个拥有 6880 亿参数的混合专家(MoE)语言模型,专为智能体应用而设计。尽管其训练的 token 数量少于其前身 A.X K1,但由于 token 效率的提高和更高质量的训练数据集,A.X K2 在各种基准测试中表现出显著的改进。该模型采用了稀疏门控注意力(SGA)等创新技术,以实现高效的长上下文处理,并采用了门控归一化(GN)技术以实现稳定的大规模训练,在 RULER 和数学任务等基准测试中取得了强劲的性能。 AI

影响 推出了一款新的大规模 MoE 模型,该模型在智能体应用和长上下文方面具有创新性,有望提升 LLM 的效率和能力。

排序理由 发布了一份详细介绍新型大型语言模型的技木报告。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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

A.X K2 语言模型发布,拥有 6880 亿参数并专注于智能体应用

本文如何被排名

Signal score
31 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
发布了一份详细介绍新型大型语言模型的技木报告。[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
model release, paper
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.AI TIER_1 Română(RO) · Cheolseung Baek, Dhammiko Arya, Eunki Kim, Gun Song, Gyoungeun Han, Hyunho Yang, Hyunjun Eun, Jin Kim, Junyoung Park, Juyun Wee, Minki Hong, Minkyung Park, Minsang Kim, Minsoo Kang, SaeRom Kim, Sangjin Kim, Sangyeol Lee, Seojin Lee, Seokhwan Jo, Seokyoun… ·

    A.X K2 技术报告

    arXiv:2608.30181v1 Announce Type: new Abstract: We introduce A.X K2, a 688B-parameter Mixture-of-Experts (MoE) language model trained from scratch as a high-performance foundation for \emph{agentic} applications. Trained on approximately 8.5T tokens---fewer than its predecessor, …