PulseAugur
中
实时 00:31:33
English(EN) Meet EmbeddingGemma 2, our first natively multimodal open model for on-device embeddings.

Google DeepMind 发布 EmbeddingGemma 2 多模态模型

作者 PulseAugur 编辑部 · [2 个来源] ·

Google DeepMind 发布了 EmbeddingGemma 2，这是一款专为设备端嵌入设计的新型开源、原生多模态模型。该模型超越了文本处理能力，能够在一个共享空间内处理和统一代码、图像、音频和视频。EmbeddingGemma 2 拥有 7.4 亿个参数，在各种基准测试中表现出竞争力，甚至超越了一些更大的专业模型，并根据 Apache 2.0 许可提供。 AI

影响 支持设备端多模态搜索，并与其它模型集成以实现私有 RAG 应用。

排序理由 前沿实验室模型发布，附带系统卡。[lever_c_降级自 frontier_release: ic=2 ai=1.0]

在 X — Google DeepMind 阅读 →

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

Google DeepMind 发布 EmbeddingGemma 2 多模态模型

本文如何被排名

Signal score
3 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
前沿实验室模型发布，附带系统卡。[lever_c_降级自 frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [2]

  1. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    拥有7.4亿参数，它在各项基准测试中均具竞争力——甚至超越了一些体量是其两倍的专业模型。

    At 740M parameters, it’s competitive across benchmarks – even outperforming some specialist models more than twice its size. Developers can use it to add multimodal search to their apps – like finding moments in a video using a voice memo – or pair it with Gemma 4 for private, h…

  2. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    认识 EmbeddingGemma 2，我们首个支持设备端嵌入的原生多模态开源模型。

    Meet EmbeddingGemma 2, our first natively multimodal open model for on-device embeddings. It expands beyond text to unify code, images, audio, and video in a shared space. 🧵 https://t.co/DC31z5viWD

相关实体

相关话题