Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

• URL: http://arxiv.org/abs/2605.27295v1
• Date: Tue, 26 May 2026 17:07:55 GMT
• Title: Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
• Abstract summary: We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space.<n>Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks.<n>We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models.
• Score: 49.70057706309715
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage the multimodal capabilities of Gemini to produce embeddings for arbitrary combinations of interleaved inputs across all these modalities that generalize well across a wide variety of tasks. Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks including unimodal, cross-modal, and multimodal retrieval spanning a diverse set of tasks. We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models. These unified capabilities make Gemini Embedding 2 a promising candidate for downstream use cases such as RAG, recommendation and search. Furthermore, its robust zero-shot performance across distinct fields - from astronomy and bioscience to fine arts and the culinary arts - establishes it as a highly reliable, out-of-the-box representation even for specialized domains.

Related papers

• One Dinomaly2 Detect Them All: A Unified Framework for Full-Spectrum Unsupervised Anomaly Detection [37.44241182701723]
  Unsupervised anomaly detection (UAD) has evolved from building specialized single-class models to unified multi-class models.<n>Dinomaly2 is the first unified framework for full-spectrum image UAD.<n>Our model achieves unprecedented 99.9% and 99.3% image-level (I-) AUROC on MVTec-AD and VisA respectively.
  arXiv  Detail & Related papers  (2025-10-20T14:57:52Z)
• TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models [23.916205754112774]
  Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks.<n>We propose TAMP, a simple yet effective pruning framework tailored for MLLMs.<n>We validate our method on two state-of-the-art MLLMs: LLaVA-NeXT, designed for vision-language tasks, and VideoLLaMA2, capable of processing audio, visual, and language modalities.
  arXiv  Detail & Related papers  (2025-04-14T05:44:38Z)
• Gemini Embedding: Generalizable Embeddings from Gemini [24.21178029650299]
  We introduce Gemini Embedding, a state-of-the-art embedding model leveraging the power of Gemini, Google's most capable large language model.<n>Capitalizing on Gemini's inherent multilingual and code understanding capabilities, Gemini Embedding produces highly generalizable embeddings for text spanning numerous languages.
  arXiv  Detail & Related papers  (2025-03-10T22:16:45Z)
• VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks [60.5257456681402]
  We study the potential for building universal embeddings capable of handling a wide range of downstream tasks.<n>We build a series of VLM2Vec models on SoTA VLMs like Phi-3.5-V, LLaVA-1.6 and evaluate them on MMEB's evaluation split.<n>Our results show that VLM2Vec achieves an absolute average improvement of 10% to 20% over existing multimodal embedding models.
  arXiv  Detail & Related papers  (2024-10-07T16:14:05Z)
• OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces [67.07083389543799]
  We present OmniBind, large-scale multimodal joint representation models ranging in scale from 7 billion to 30 billion parameters. Due to the scarcity of data pairs across all modalities, instead of training large models from scratch, we propose remapping and binding the spaces of various pre-trained specialist models together. Experiments demonstrate the versatility and superiority of OmniBind as an omni representation model, highlighting its great potential for diverse applications.
  arXiv  Detail & Related papers  (2024-07-16T16:24:31Z)
• SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation [61.392147185793476]
  We present a unified and versatile foundation model, namely, SEED-X.<n>SEED-X is able to model multi-granularity visual semantics for comprehension and generation tasks.<n>We hope that our work will inspire future research into what can be achieved by versatile multimodal foundation models in real-world applications.
  arXiv  Detail & Related papers  (2024-04-22T17:56:09Z)
• Noise-powered Multi-modal Knowledge Graph Representation Framework [52.95468915728721]
  The rise of Multi-modal Pre-training highlights the necessity for a unified Multi-Modal Knowledge Graph representation learning framework.<n>We propose a novel SNAG method that utilizes a Transformer-based architecture equipped with modality-level noise masking.<n>Our approach achieves SOTA performance across a total of ten datasets, demonstrating its versatility.
  arXiv  Detail & Related papers  (2024-03-11T15:48:43Z)
• Generative Multimodal Models are In-Context Learners [60.50927925426832]
  We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences. Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning.
  arXiv  Detail & Related papers  (2023-12-20T18:59:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.