# OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces

arXiv: https://arxiv.org/abs/2407.11895 · HTML: https://mlsanity.com/paper/2407.11895/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 73 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 30 of 58)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)

## Built on by (most cited first, 30 of 39)

- [Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration](https://mlsanity.com/paper/2505.20256/) (2025)
- [Chat-Driven Text Generation and Interaction for Person Retrieval](https://mlsanity.com/paper/2509.12662/) (2025)
- [Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval](https://mlsanity.com/paper/2505.19650/) (2025)
- [MIO: A Foundation Model on Multimodal Tokens](https://mlsanity.com/paper/2409.17692/) (2024)
- [Continual Multimodal Contrastive Learning](https://mlsanity.com/paper/2503.14963/) (2025)
- [Principled Multimodal Representation Learning](https://mlsanity.com/paper/2507.17343/) (2025)
- [OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination](https://mlsanity.com/paper/2509.00723/) (2025)
- [The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment](https://mlsanity.com/paper/2511.21331/) (2025)
- [Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations](https://mlsanity.com/paper/2410.02086/) (2024)
- [DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification](https://mlsanity.com/paper/2504.10985/) (2025)
- [Learning Shared Representations from Unpaired Data](https://mlsanity.com/paper/2505.21524/) (2025)
- [Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning](https://mlsanity.com/paper/2410.10913/) (2024)
- [Calibrated Multimodal Representation Learning with Missing Modalities](https://mlsanity.com/paper/2511.12034/) (2025)
- [Efficient and High-Fidelity Omni Modality Retrieval](https://mlsanity.com/paper/2603.02098/) (2026)
- [Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio](https://mlsanity.com/paper/2607.18666/) (2026)
- [Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities](https://mlsanity.com/paper/2511.11512/) (2025)
- [The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models](https://mlsanity.com/paper/2601.08876/) (2026)
- [TextME: Bridging Unseen Modalities Through Text Descriptions](https://mlsanity.com/paper/2602.03098/) (2026)
- [EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models](https://mlsanity.com/paper/2604.11043/) (2026)
- [Grounding Intelligence in Movement](https://mlsanity.com/paper/2507.02771/) (2025)
- [ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology](https://mlsanity.com/paper/2511.02946/) (2025)
- [EBind: a practical approach to space binding](https://mlsanity.com/paper/2511.14229/) (2025)
- [TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment](https://mlsanity.com/paper/2601.19247/) (2026)
- [Binding Multiple Modalities via Multimodal Wasserstein Barycenter](https://mlsanity.com/paper/2609.33800/) (2026)
- [SounDiT: Geo-Contextual Soundscape-to-Landscape Generation](https://mlsanity.com/paper/2505.12734/) (2025)
- [SCENEFORGE: Enhancing 3D-text alignment with Structured Scene Compositions](https://mlsanity.com/paper/2509.15693/) (2025)
- [MAJORScore: A Novel Metric for Evaluating Multimodal Relevance via Joint Representation](https://mlsanity.com/paper/2509.21365/) (2025)
- [Cross-modal Counterfactual Explanations: Uncovering Decision Factors and Dataset Biases in Subjective Classification](https://mlsanity.com/paper/2512.18864/) (2025)
- [A Vision for Multisensory Intelligence: Sensing, Science, and Synergy](https://mlsanity.com/paper/2601.04563/) (2026)
- [BrokenBind: Universal Modality Exploration beyond Dataset Boundaries](https://mlsanity.com/paper/2602.06451/) (2026)

## Abstract (arXiv)

Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Given the foundational role of multimodal joint representation in understanding and generation pipelines, high-quality omni joint representations would be a step toward co-processing more diverse multimodal information. In this work, we present OmniBind, large-scale multimodal joint representation models ranging in scale from 7 billion to 30 billion parameters, which support 3D, audio, image, and language inputs. 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. This approach enables "scaling up" by indirectly increasing the model parameters and the amount of seen data. To effectively integrate various spaces, we dynamically assign weights to different spaces by learning routers with two objectives: cross-modal overall alignment and language representation decoupling. Notably, since binding and routing spaces both only require lightweight networks, OmniBind is extremely training-efficient. Learning the largest 30B model requires merely unpaired unimodal data and approximately 3 days on a single 8-4090 node. Extensive experiments demonstrate the versatility and superiority of OmniBind as an omni representation model, highlighting its great potential for diverse applications, such as any-query and composable multimodal understanding.