Paper page - EmbeddingGemma 2: Unified and Efficient Multimodal Representations

Source: https://huggingface.co/papers/2610.37364 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

EmbeddingGemma 2 is an open multimodal embedding model that unifies text, images, audio, and video representations with efficient resource-flexible design and state-of-the-art benchmark performance.

We present EmbeddingGemma 2, an openmultimodal embedding modelwhich natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach introduces improvements such as simplifiedper-layer embeddingsand amulti-stage curriculumwith modality and objective progression which ensure strong quality across unimodal,cross-modal, andmixed-modalevaluations. Notably, in comprehensive embedding benchmarks across all modalities, EmbeddingGemma 2 establishes a newPareto frontier, outperforming both specialist models and models two to twelve times larger. Furthermore, our design offers flexibility for resource-constrained environments, supportingselective modality encoder loading, adjustablevision token budgets,truncatable embedding dimensions, andquantized weights. We present ablations analyzing key decisions and release EmbeddingGemma 2 to promote further research.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2610\.37364

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### google/embeddinggemma-2 Feature Extraction• 0.7B• Updatedabout 10 hours ago • 283k • 2.99k

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.37364 in a dataset README.md to link it from this page.

Spaces citing this paper46

Browse 46 spaces citing this paper## Collections including this paper1