PulseAugur
EN
LIVE 19:00:33
Italiano(IT) 🧠 # Google DeepMind rilascia # EmbeddingGemma 2: testo, immagini, audio e video diventano confrontabili nello stesso spazio di embedding, per cercare tra format

Google releases EmbeddingGemma 2 for cross-modal search

By PulseAugur Editorial · [2 sources] ·

Google has released EmbeddingGemma 2, an open model capable of processing and embedding multiple data types including text, code, images, video, and audio into a single vector space. This allows for cross-modal search, enabling users to query for specific moments in videos or content within scanned documents using text prompts. The 740M parameter model operates under an Apache 2.0 license and integrates different media tokens into a unified sequence for a single encoder. AI

IMPACT Enables more sophisticated cross-modal search and retrieval across diverse data types.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Google releases EmbeddingGemma 2 for cross-modal search

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card. [lever_c_demoted from 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
24 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. Mastodon — mastodon.social TIER_1 English(EN) · theskumar ·

    EmbeddingGemma 2 ( https:// blog.google/innovation-and-ai/ technology/developers-tools/embeddinggemma-2/ ) puts text, code, images, video and audio (or a mix) i

    EmbeddingGemma 2 ( https:// blog.google/innovation-and-ai/ technology/developers-tools/embeddinggemma-2/ ) puts text, code, images, video and audio (or a mix) into one 768-dimension vector, from a 740M open model under Apache 2.0. Image, video and audio tokens are spliced into th…

    LINKS blog.google/…/embeddinggemma-2 saurabh-kumar.com/…/2026-10-25.html blog.google/innovation-and-ai
  2. Mastodon — mastodon.social TIER_1 Italiano(IT) · [email protected] ·

    🧠 Google DeepMind releases EmbeddingGemma 2: text, images, audio, and video become comparable in the same embedding space, for searching across formats

    🧠 # Google DeepMind rilascia # EmbeddingGemma 2: testo, immagini, audio e video diventano confrontabili nello stesso spazio di embedding, per cercare tra formati diversi direttamente sul dispositivo. 👉 I dettagli: https:// lnkd.in/p/dHuVUKuS ___ ✉️ 𝗦𝗲 𝘃𝘂𝗼𝗶 𝗿𝗶𝗺𝗮𝗻𝗲𝗿𝗲 𝗮𝗴𝗴𝗶𝗼𝗿𝗻𝗮𝘁𝗼/𝗮 𝘀…

    LINKS linkedin.com/…/alessiopomaro_google-embed… alessiopomaro.it

RELATED ENTITIES

RELATED TOPICS