PulseAugur
中
实时 17:59:29
English(EN) K-EXAONE 2.0 Technical Report

LG AI Research 发布 K-EXAONE 2.0，拥有 7500 亿参数和 256K 上下文

作者 PulseAugur 编辑部 · [2 个来源] ·

LG AI Research 发布了 K-EXAONE 2.0，这是一个开放权重多语言基础模型。这个更新的专家混合模型拥有 7500 亿总参数，每个 token 激活约 370 亿参数，显著增加了其容量。K-EXAONE 2.0 支持 256K token 的上下文长度，将多语言能力扩展到十种语言，并在智能体编码和长上下文理解方面显示出显著的改进。该模型在 Apache 2.0 许可下发布，鼓励更广泛的生态系统发展。 AI

影响 此次发布为研究人员和开发人员提供了一个强大的开放权重基础模型，有可能加速多语言人工智能和长上下文理解方面的进步。

排序理由 详细介绍新开放权重模型发布的技朧报告。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

LG AI Research 发布 K-EXAONE 2.0，拥有 7500 亿参数和 256K 上下文

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
Research
详细介绍新开放权重模型发布的技朧报告。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
64 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 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Eunbi Choi, Kibong Choi, Sehyun Chun, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Ahra Jo, Hyunjik Jo, Yeonsik Jo, Minhyeok Jung, Doyoung Kim, Heegyu Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Byungoh Ko, Changhun Le… ·

    K-EXAONE 2.0 技术报告

    arXiv:2608.04505v1 Announce Type: new Abstract: This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcy…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    K-EXAONE 2.0 技术报告

    This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcycle K-EXAONE and expand its architecture, yieldi…

相关实体

相关话题