# jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

arXiv: https://arxiv.org/abs/2605.08384 · HTML: https://mlsanity.com/paper/2605.08384/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval](https://mlsanity.com/paper/2406.04292/) (2024)
- [ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval](https://mlsanity.com/paper/2505.17166/) (2025)
- [jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images](https://mlsanity.com/paper/2412.08802/) (2024)
- [MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin](https://mlsanity.com/paper/2310.14037/) (2023)
- [Scaling Language-Centric Omnimodal Representation Learning](https://mlsanity.com/paper/2510.11693/) (2025)
- [jina-embeddings-v5-text: Task-Targeted Embedding Distillation](https://mlsanity.com/paper/2602.15547/) (2026)
- [Nomic Embed Vision: Expanding the Latent Space](https://mlsanity.com/paper/2406.18587/) (2024)
- [MIEB: Massive Image Embedding Benchmark](https://mlsanity.com/paper/2504.10471/) (2025)
- [e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings](https://mlsanity.com/paper/2601.03666/) (2026)

## Built on by (most cited first, 5 of 5)

- [Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio](https://mlsanity.com/paper/2607.18666/) (2026)
- [KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval](https://mlsanity.com/paper/2608.01389/) (2026)
- [Modality-Gated Deep Adapters: Adding a Modality to a Frozen Embedding Model with Exact Preservation](https://mlsanity.com/paper/2609.26182/) (2026)
- [MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos](https://mlsanity.com/paper/2609.28437/) (2026)
- [RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces](https://mlsanity.com/paper/2610.05852/) (2026)

## Abstract (arXiv)

In this work, we introduce GELATO (Geometry-preserving Embeddings via Locked Aligned TOwers), a novel approach to multimodal embedding models. We build on the VLM-style architecture, in which non-text encoders are adapted to produce input for a language model, which in turn generates embeddings for all varieties of input. We present the result: the jina-embeddings-v5-omni suite, a pair of models that encode text, image, audio, and video input into a single semantic embedding space. GELATO extends the two Jina Embeddings v5 Text models to support additional modality by adding encoders for images and audio. The backbone text embedding models and the added non-text modality encoders remain frozen. We only trained the connecting components, representing 0.35% of the total weights of the joint model. Training is therefore much more efficient than full-parameter retraining. Additionally, the language model remains effectively unaltered, producing exactly the same embeddings for text inputs as the Jina Embeddings v5 Text models. Our evaluations show that GELATO produces results that are competitive with the state-of-the-art, yielding nearly equal performance to larger multimodal embedding models.